© 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. 31-GEMMASCOPE-2-RES-16K
    4. 10860
    Prev
    Next
    INDEX
    Explanations

    rdata, s=, r/, dg/n, nsecs, m/v, vbox, s or, t=, mso

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

    This neuron strongly activates on isolated uppercase-letter tokens or short alphanumeric codes (e.g. single capital letters or letter­digit sequences) that serve as identifiers.

    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_31_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
    rium
    0.38
    चालित
    0.37
    ég
    0.37
    otros
    0.36
    िज़
    0.34
    î
    0.33
    ellan
    0.32
     reimag
    0.32
    ën
    0.32
    گە
    0.32
    POSITIVE LOGITS
    스가
    0.46
     첫
    0.43
    오
    0.39
     শ্রীমতি
    0.39
     findViewById
    0.38
    []=
    0.38
    highscore
    0.38
    pstmt
    0.38
     fname
    0.37
    fname
    0.37
    Activations Density 0.093%

    No Known Activations