© 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. 245523
    Prev
    Next
    INDEX
    Explanations

    chiropractic appointment, extended butane, victorian terrace

    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
    聸
    0.46
    擔心
    0.44
    法國
    0.44
    ოვნ
    0.44
     বক্তৃতা
    0.44
    ᓪ
    0.44
     Equity
    0.43
    equity
    0.43
     जर्मनी
    0.43
    Equity
    0.42
    POSITIVE LOGITS
    giờ
    0.49
    憾
    0.44
     hissed
    0.44
     xas
    0.43
    []{
    0.42
    只有
    0.41
     khắc
    0.40
    VHS
    0.40
    द्रता
    0.40
     releases
    0.40
    Activations Density 0.000%

    No Known Activations