© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11167
    Prev
    Next
    INDEX
    Explanations

    chemical names and formulas

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

    The neuron strongly responds to numeric tokens (digits and numbers), especially those appearing in chemical names, formulas, citations, or other numeric data.

    oai_token-act-pair · o4-miniTriggered 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
    >/
    0.63
     NYC
    0.62
     capaz
    0.60
     >
    0.60
     godz
    0.59
     ロゴ
    0.59
     wiggle
    0.59
    z
    0.57
     podob
    0.56
     "/
    0.56
    POSITIVE LOGITS
     Examining
    0.76
     Appraisal
    0.73
     Bhagavato
    0.70
    Ethics
    0.70
    ρη
    0.68
     Descriptive
    0.66
    ‏:‏
    0.66
    ടതി
    0.65
     Sanitation
    0.65
     Ethics
    0.64
    Activations Density 0.003%

    No Known Activations