© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 221171
    Prev
    Next
    INDEX
    Explanations

    name, owners, support, printing

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

    focus on specific aspects

    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
    Negative Logits
    ){
    0.48
    і
    0.46
    "
    0.45
    co
    0.44
    е
    0.44
    benzoimidazol
    0.43
    éc
    0.43
    <unused976>
    0.43
    transform
    0.43
     reacción
    0.42
    POSITIVE LOGITS
    𐰖
    0.49
    ધો
    0.49
    MARKED
    0.49
     adı
    0.47
    NameTo
    0.47
    aadhar
    0.46
    FAPI
    0.46
    有り
    0.46
    കര
    0.45
    Owners
    0.45
    Activations Density 0.001%

    No Known Activations