© 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. 232467
    Prev
    Next
    INDEX
    Explanations

    contact us

    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
     času
    0.48
     trama
    0.45
     kra
    0.43
     timeCounter
    0.42
     Roc
    0.41
    time
    0.41
     краю
    0.41
     hunk
    0.40
    endTime
    0.40
    时
    0.40
    POSITIVE LOGITS
    ifizieren
    0.55
     injectable
    0.49
    primarily
    0.48
    儀
    0.48
    鰓
    0.47
    利的
    0.47
    𒉌
    0.46
    ির
    0.46
    鉢
    0.46
    尭
    0.46
    Activations Density 0.001%

    No Known Activations