© 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. 123883
    Prev
    Next
    INDEX
    Explanations

    local clients, rights, rent, only two

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

    building apps

    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
    ،
    0.55
    !
    0.52
    Vector
    0.51
     (
    0.50
    Benefits
    0.49
     MUS
    0.49
    Types
    0.47
    Added
    0.46
     IBS
    0.46
    Routes
    0.46
    POSITIVE LOGITS
    achu
    0.54
    及び
    0.52
    SERVICIO
    0.50
    ನ
    0.50
    ész
    0.48
    埓
    0.48
    izacja
    0.47
    membered
    0.47
    izquierda
    0.47
    ügen
    0.46
    Activations Density 0.000%

    No Known Activations