© 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. 31078
    Prev
    Next
    INDEX
    Explanations

    ending punctuation

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

    introducing lists

    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
    ötz
    0.52
    <unused2173>
    0.52
    지와
    0.50
    とその
    0.49
     protože
    0.49
    <unused2180>
    0.48
     takže
    0.46
     but
    0.46
    Ä
    0.46
    ずに
    0.44
    POSITIVE LOGITS
    ،
    1.42
    ，
    1.28
     ،
    1.09
    ,
    1.05
     ,
    1.03
    ၊
    1.01
    $,
    0.95
    ,,
    0.95
    ፣
    0.94
    %,
    0.93
    Activations Density 0.133%

    No Known Activations