© 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. 223983
    Prev
    Next
    INDEX
    Explanations

    little older, protect the, done by

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

    seed, cult, funds

    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
    in
    0.79
    P
    0.61
    In
    0.55
    as
    0.54
    p
    0.54
    I
    0.54
    ar
    0.53
    IN
    0.53
    T
    0.53
    ie
    0.52
    POSITIVE LOGITS
     dosimetry
    0.52
     cricketer
    0.49
     toxicology
    0.47
     histidine
    0.47
    藪
    0.47
     भाज
    0.46
    _{*}$
    0.45
     covariates
    0.45
     annuelle
    0.44
    を知
    0.44
    Activations Density 0.001%

    No Known Activations