© 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. 191114
    Prev
    Next
    INDEX
    Explanations

    counting and numerical sequencing

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

    foreign language or punctuation

    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
    atá
    0.46
    apache
    0.45
    Proxy
    0.45
    多少
    0.45
    sender
    0.43
    ية
    0.43
    vendo
    0.43
    贺
    0.43
    quanto
    0.43
    Fri
    0.43
    POSITIVE LOGITS
     DEPARTMENT
    0.51
     AMS
    0.48
     EMERG
    0.48
     Militar
    0.47
    quarie
    0.46
     fertilization
    0.46
     trifling
    0.45
     Verbesser
    0.45
    ற
    0.45
     implantation
    0.45
    Activations Density 0.000%

    No Known Activations