© 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. 138585
    Prev
    Next
    INDEX
    Explanations

    last keeper, promised production, grid layout

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

    bird or car in game code

    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
     Descent
    0.48
    Neighbor
    0.46
    ركة
    0.45
    كين
    0.44
     wichtig
    0.44
    Sony
    0.43
    Folders
    0.42
    y
    0.42
    يير
    0.42
     হোমিওপ্যাথিক
    0.42
    POSITIVE LOGITS
     최대
    0.52
     இந்தியா
    0.48
     문화
    0.47
    ಬ್ಬಿಣ
    0.47
     금
    0.46
     최대한
    0.46
     구분
    0.46
     기반
    0.46
     시민
    0.46
    hayati
    0.46
    Activations Density 0.000%

    No Known Activations