© 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. 116308
    Prev
    Next
    INDEX
    Explanations

    defends their thesis

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

    classification and prediction

    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
    жит
    0.56
    ټر
    0.53
    🤖
    0.53
    midd
    0.49
    unile
    0.49
    の新
    0.48
    گیز
    0.47
    ヱ
    0.46
    speakers
    0.46
    가가
    0.46
    POSITIVE LOGITS
     Fighting
    0.45
     Violent
    0.45
              
    0.43
     Mouth
    0.43
     Consecutive
    0.43
     Harcourt
    0.43
     NER
    0.42
     ಇದರ
    0.42
                              
    0.42
                               
    0.42
    Activations Density 0.000%

    No Known Activations