© 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. 239636
    Prev
    Next
    INDEX
    Explanations

    Bookmark the permalink

    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
    arians
    0.51
    `,
    0.42
    ?",
    0.42
    arsen
    0.42
    ,"
    0.41
    t
    0.41
    ش
    0.41
    PI
    0.40
     불안
    0.40
    ilim
    0.40
    POSITIVE LOGITS
     acht
    0.54
     nemá
    0.54
     année
    0.52
    ஞ்ஞான
    0.50
     vier
    0.50
    เวลา
    0.50
     año
    0.49
    rà
    0.49
     januar
    0.49
    行業
    0.49
    Activations Density 0.001%

    No Known Activations