© 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. 18922
    Prev
    Next
    INDEX
    Explanations

    specific terms followed by descriptions

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

    checkout. checkin/checkout

    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
    ށް
    0.49
    άσ
    0.45
    োপাধ্যায়
    0.44
     లు
    0.43
     విజ
    0.43
    嗬
    0.43
    ümüş
    0.42
    ждён
    0.42
     తెర
    0.42
    购物车
    0.42
    POSITIVE LOGITS
     Right
    0.40
     Neumann
    0.40
     may
    0.40
    ↵↵
    0.39
    ira
    0.39
     was
    0.39
     also
    0.39
     Committee
    0.39
    ich
    0.38
    ?
    0.38
    Activations Density 0.006%

    No Known Activations