© 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. 177004
    Prev
    Next
    INDEX
    Explanations

    published on dates

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

    conclusion: section ending

    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
    ي
    0.72
    i
    0.55
     خواست
    0.51
    +"|
    0.47
    Θ
    0.46
    CLE
    0.46
    NIH
    0.45
     Ontology
    0.45
    HTML
    0.45
     ô
    0.45
    POSITIVE LOGITS
    рал
    0.50
    опера
    0.45
    <unused2107>
    0.43
     Verme
    0.43
     таким
    0.43
    semos
    0.42
     वर्मा
    0.42
     EFFECTS
    0.41
    евич
    0.41
     protože
    0.41
    Activations Density 0.000%

    No Known Activations