© 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. 154734
    Prev
    Next
    INDEX
    Explanations

    liability and subsequent actions

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

    learning, judging, witness

    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
    블
    0.53
     módulos
    0.47
    MODEL
    0.46
    obil
    0.45
    лил
    0.45
     модуль
    0.45
    赵
    0.45
    кл
    0.44
    wool
    0.44
    ী
    0.44
    POSITIVE LOGITS
     هست
    0.54
     ہے
    0.51
    )!
    0.50
     lotta
    0.47
    ！)
    0.47
     तुम्ह
    0.47
     ונ
    0.47
     तुम्हारा
    0.46
    exit
    0.46
    នឹង
    0.46
    Activations Density 0.000%

    No Known Activations