© 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. 107906
    Prev
    Next
    INDEX
    Explanations

    party invitations

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

    define your "why"

    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
    宠
    0.45
     orderBy
    0.44
    ホテル
    0.43
    வசம்
    0.43
    莗
    0.43
    वन
    0.42
    ্টেন
    0.42
     airline
    0.42
     fadeInLeft
    0.41
    锜
    0.41
    POSITIVE LOGITS
     tinker
    0.47
    ällen
    0.45
    philosoph
    0.45
    discrimin
    0.44
     সংসারে
    0.44
    isenberg
    0.44
    universe
    0.44
    dit
    0.44
    disciplinary
    0.43
    classified
    0.43
    Activations Density 0.007%

    No Known Activations