© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 477
    Prev
    Next
    INDEX
    Explanations

    abstract domains and structures

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects quantitative scientific measurements (numerical values, especially decimal results) in technical text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    technical or scientific text discussing complex systems, processes, or mechanisms.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    technical head nouns in scientific compound phrases—names of systems, processes, structures, or measured quantities in formal text

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Counc
    0.44
    นี่
    0.44
    Supreme
    0.43
    回家
    0.43
    ขาย
    0.43
    Money
    0.42
    ប្រើ
    0.42
    Business
    0.42
    House
    0.42
    HOUSE
    0.42
    POSITIVE LOGITS
     heterogeneity
    0.57
     tumorigen
    0.54
     および
    0.53
     proliferative
    0.52
    进而
    0.52
     plasticity
    0.51
     xhrObj
    0.50
     myocardium
    0.50
     concomit
    0.49
     proinflammatory
    0.48
    Activations Density 0.000%

    No Known Activations