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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5905
    Prev
    Next
    INDEX
    Explanations

    numbers and code tags

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    claims
    0.59
    references
    0.55
    тому
    0.54
    azze
    0.53
    fh
    0.51
    chemia
    0.51
    たとえば
    0.50
    鄯
    0.50
     fluctu
    0.50
    vindos
    0.50
    POSITIVE LOGITS
     Eugene
    0.54
     Gaelic
    0.53
     por
    0.52
     Anyways
    0.52
    ֑
    0.52
     Simulator
    0.51
     emulator
    0.51
    ್ರೆ
    0.51
     OCR
    0.51
     ATP
    0.51
    Activations Density 0.001%

    No Known Activations