© 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. 120521
    Prev
    Next
    INDEX
    Explanations

    roles, concepts, and places

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

    WebUSB, spreading, error handling

    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
    are
    0.53
    Veg
    0.50
    as
    0.49
    ،
    0.49
    ire
    0.48
     Educ
    0.45
    mm
    0.45
    arma
    0.44
    season
    0.44
     Are
    0.43
    POSITIVE LOGITS
     tampoco
    0.50
    ੋਰ
    0.49
     появилась
    0.49
    ဝန်
    0.49
     añadi
    0.49
     nuestra
    0.47
    뭡
    0.47
     apare
    0.46
     histórica
    0.45
     giapp
    0.45
    Activations Density 0.000%

    No Known Activations