© 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. 112004
    Prev
    Next
    INDEX
    Explanations

    game pin or Twitch community

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

    technical topics and concepts

    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
     compartido
    0.48
    ന്തപു
    0.48
    isVideoRecording
    0.47
     సహాయ
    0.45
     枚
    0.44
     bson
    0.44
     시즌
    0.43
     ተጨማሪ
    0.43
    サービスの
    0.43
     מת
    0.43
    POSITIVE LOGITS
    -
    0.54
    1
    0.48
    (
    0.47
    awa
    0.47
    ina
    0.46
    /
    0.46
    I
    0.45
     banning
    0.44
    ING
    0.44
    There
    0.43
    Activations Density 0.001%

    No Known Activations