© 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. 12563
    Prev
    Next
    INDEX
    Explanations

    questions, requests for help

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

    The neuron activates on ordinal or list‐style headings and numbering (e.g. Roman numerals, “first order,” section/list markers).

    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
    ▬
    0.87
    водитель
    0.84
     ASTM
    0.84
    RFID
    0.83
    rard
    0.81
    vrd
    0.81
     EXAMINATION
    0.80
    𝒽
    0.80
    nV
    0.80
     CFRP
    0.79
    POSITIVE LOGITS
     contenu
    0.78
    onaise
    0.75
    newState
    0.73
    ık
    0.71
     gets
    0.70
    icules
    0.70
     toutes
    0.68
    掻
    0.68
     eine
    0.66
     getText
    0.66
    Activations Density 0.000%

    No Known Activations