© 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. 63282
    Prev
    Next
    INDEX
    Explanations

    packaging errors

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

    login credentials and details

    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
    <start_of_image>
    0.50
    _
    0.49
    r
    0.47
    valued
    0.44
    ball
    0.43
    ↵
    0.43
    est
    0.43
    Park
    0.43
    valu
    0.42
    ID
    0.41
    POSITIVE LOGITS
    乸
    0.52
    蒖
    0.51
     იქ
    0.49
     LOTRAchievement
    0.49
    ერი
    0.49
     இருப்பதால்
    0.49
    гъл
    0.48
    價格
    0.48
     જન્મદિવસ
    0.48
     নিয়ে
    0.48
    Activations Density 0.000%

    No Known Activations