© 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. 212612
    Prev
    Next
    INDEX
    Explanations

    report generate

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

    edge computing, digestion, limitations, menu

    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
     수학
    0.47
     법
    0.47
     券
    0.45
     bilo
    0.45
    不管是
    0.43
     a
    0.43
     ş
    0.43
     DATA
    0.42
     čas
    0.42
     ř
    0.42
    POSITIVE LOGITS
    सेवी
    0.49
    वीपी
    0.45
    authored
    0.44
    gameObjects
    0.43
    ларын
    0.43
    irte
    0.43
    +
    0.43
    insertion
    0.42
    ச்செய
    0.42
    agés
    0.42
    Activations Density 0.002%

    No Known Activations