© 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. 166482
    Prev
    Next
    INDEX
    Explanations

    sports miss or conversion

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

    credential

    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
    8
    0.52
     e
    0.48
     Receive
    0.47
    6
    0.47
    ရာ
    0.45
     Received
    0.45
     Raise
    0.44
    4
    0.44
     Image
    0.43
     Priorities
    0.43
    POSITIVE LOGITS
    dauer
    0.55
    лій
    0.53
    gangenheit
    0.53
     necesariamente
    0.51
     representada
    0.48
    guez
    0.48
     güzel
    0.47
     prennent
    0.47
     crean
    0.47
    también
    0.47
    Activations Density 0.001%

    No Known Activations