© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 58109
    Prev
    Next
    INDEX
    Explanations

    full unfinished

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

    concession or contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    Type
    0.45
     ভোগের
    0.44
    u
    0.44
    Premium
    0.44
     ->
    0.43
    ↵
    0.43
    agg
    0.42
    deleted
    0.42
    Security
    0.41
    У
    0.41
    POSITIVE LOGITS
    եր
    0.47
    ሟ
    0.46
     fáb
    0.46
     censor
    0.46
     సంవత్స
    0.44
     צ
    0.43
     allemande
    0.43
    ሳ
    0.43
     λεπ
    0.43
     일으
    0.43
    Activations Density 0.000%

    No Known Activations