© 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. 79115
    Prev
    Next
    INDEX
    Explanations

    metadata is

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

    state variation ROI apply

    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
    t
    0.48
    EXP
    0.46
    bed
    0.45
    ticks
    0.45
    tokenize
    0.44
     repris
    0.44
    Recently
    0.44
    retry
    0.44
    AMS
    0.43
    ชาย
    0.42
    POSITIVE LOGITS
     Joc
    0.57
    غرافيا
    0.49
    сат
    0.49
    闶
    0.49
     sessão
    0.48
     اطلاعات
    0.48
    ાઇલ
    0.47
     tiếng
    0.46
     ойно
    0.45
     Palabra
    0.45
    Activations Density 0.000%

    No Known Activations