© 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. 60645
    Prev
    Next
    INDEX
    Explanations

    article stub expansion

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

    laceration or deep cut

    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
     ম্যাচে
    0.41
     분명
    0.41
    źnie
    0.38
     ধৈর্য
    0.36
    BEFORE
    0.36
    신기
    0.36
    쟤
    0.35
    元の
    0.35
     AGAIN
    0.35
    никова
    0.35
    POSITIVE LOGITS
    entric
    0.45
     要
    0.43
     cri
    0.43
     vuole
    0.42
    cri
    0.41
    iav
    0.40
     SWOT
    0.40
    iga
    0.40
     Lietuvos
    0.40
    स्था
    0.39
    Activations Density 0.000%

    No Known Activations