© 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. 47255
    Prev
    Next
    INDEX
    Explanations

    problem or issue with

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

    suitability and challenges

    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
     h
    0.46
     öffentlichen
    0.46
     public
    0.45
     sanitized
    0.44
     component
    0.43
     東京都
    0.43
     serialized
    0.42
    component
    0.41
     Component
    0.41
     그러니까
    0.41
    POSITIVE LOGITS
    omanip
    0.55
    자가
    0.53
    ੱਚ
    0.52
    <unused50>
    0.49
    初心者
    0.49
    jeva
    0.47
    چے
    0.47
     바랍니다
    0.47
    आपका
    0.47
     Milit
    0.46
    Activations Density 0.000%

    No Known Activations