© 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. 155806
    Prev
    Next
    INDEX
    Explanations

    asking questions or discussing results

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

    be hated than ignored

    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
     descenso
    0.49
     և
    0.46
     dirige
    0.44
    mainframe
    0.44
    ława
    0.44
    领导
    0.43
    _
    0.42
    决定
    0.42
    ଲା
    0.42
    Branches
    0.42
    POSITIVE LOGITS
     ถาม
    0.48
     掛け
    0.48
     Mileage
    0.48
     結果
    0.47
    isku
    0.47
    mens
    0.46
    лія
    0.46
     Kapol
    0.45
     Garmin
    0.45
     Quantity
    0.44
    Activations Density 0.000%

    No Known Activations