© 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. 232666
    Prev
    Next
    INDEX
    Explanations

    Clin work Nov

    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
     γνω
    0.47
     pleasantly
    0.47
    ಮೆ
    0.45
     επιχει
    0.43
     regularly
    0.43
     températures
    0.42
     (_)
    0.42
     ")";
    0.42
    liers
    0.42
     inaugur
    0.42
    POSITIVE LOGITS
    <0x93>
    0.54
    จน
    0.47
     distX
    0.47
     Clin
    0.47
     Padd
    0.47
     клини
    0.45
    憎
    0.45
     clínicos
    0.45
    🍟
    0.45
    काला
    0.44
    Activations Density 0.000%

    No Known Activations