© 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. 210404
    Prev
    Next
    INDEX
    Explanations

    mount belt clip

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

    distracted by or ability to incorporate

    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
    ׄ
    0.50
    འི་
    0.46
    ле
    0.46
     químico
    0.46
    reqParams
    0.45
     thisStudent
    0.45
     самым
    0.45
     newToken
    0.45
    Retour
    0.44
    最大の
    0.44
    POSITIVE LOGITS
     Connecting
    0.50
     Adaptation
    0.46
    .%
    0.45
     foraging
    0.45
     Sert
    0.44
     heter
    0.43
     वापरा
    0.43
     District
    0.42
     trespassing
    0.42
     AngularJS
    0.41
    Activations Density 0.000%

    No Known Activations