© 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. 60956
    Prev
    Next
    INDEX
    Explanations

    ISO standards and projects

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

    asking why / believed

    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
    یە
    0.50
     gate
    0.49
    อาด
    0.45
    ้อน
    0.45
    '
    0.43
     December
    0.41
    емое
    0.41
    (
    0.40
     magnet
    0.40
    EMA
    0.40
    POSITIVE LOGITS
     outras
    0.61
     சர்
    0.56
     francês
    0.54
    Otros
    0.54
     другому
    0.54
     französ
    0.54
     રૂપિયા
    0.54
     மெ
    0.53
     homens
    0.53
     كيلو
    0.52
    Activations Density 0.000%

    No Known Activations