© 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. 2927
    Prev
    Next
    INDEX
    Explanations

    Japanese and non-English words

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

    conversational interjections and affirmations

    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
    Advisor
    0.56
     onboarding
    0.52
     workspaces
    0.51
     phasor
    0.51
     yourself
    0.50
     adju
    0.49
    :</
    0.48
     intang
    0.48
     Quote
    0.47
     Workflow
    0.47
    POSITIVE LOGITS
    www
    0.63
    .
    0.63
    mu
    0.57
    結婚
    0.57
    勝利
    0.57
    {
    0.56
    今日は
    0.54
    人
    0.54
    <0x80>
    0.53
    мерикан
    0.53
    Activations Density 0.218%

    No Known Activations