© 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. 102735
    Prev
    Next
    INDEX
    Explanations

    grace, before, separate, many, census

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

    lists of options or choices

    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
     വി
    0.52
     Czy
    0.49
    壃
    0.47
     आगे
    0.47
     অনে
    0.47
     Cambio
    0.47
    ែល
    0.46
    મ
    0.46
     Ejec
    0.46
     Przed
    0.46
    POSITIVE LOGITS
    knowledge
    0.50
    <strong>
    0.50
    information
    0.49
     sprints
    0.49
    intervention
    0.48
    behavior
    0.46
    oriented
    0.46
    Social
    0.45
    R
    0.45
    intent
    0.45
    Activations Density 0.001%

    No Known Activations