© 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. 12906
    Prev
    Next
    INDEX
    Explanations

    financial reporting and revisions

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

    toasting

    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
     totiž
    0.52
    ''}
    0.51
     atractivo
    0.47
     consecutivos
    0.47
     ethnicity
    0.46
    ...";
    0.46
     시리즈
    0.45
    スン
    0.45
     raza
    0.45
    முடிய
    0.44
    POSITIVE LOGITS
    ,
    0.60
     ,
    0.52
     Zealand
    0.52
     Shr
    0.49
     Kent
    0.48
     Elephant
    0.47
     Ste
    0.47
     Folding
    0.45
     Machine
    0.45
    Elephant
    0.44
    Activations Density 0.000%

    No Known Activations