© 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. 86753
    Prev
    Next
    INDEX
    Explanations

    references for information

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

    connections and integrations

    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
    ,
    0.54
    ;
    0.44
     роки
    0.44
    iemi
    0.43
     оча
    0.42
     bụ
    0.41
     Россию
    0.41
    uhe
    0.41
    ,*
    0.41
     angust
    0.41
    POSITIVE LOGITS
    écart
    0.51
    ঞ্জন
    0.48
    stackoverflow
    0.47
    stacked
    0.47
    готовки
    0.47
    reflective
    0.47
    errorHandler
    0.46
    advantage
    0.46
    unless
    0.46
    마트
    0.46
    Activations Density 0.000%

    No Known Activations