© 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. 85098
    Prev
    Next
    INDEX
    Explanations

    service offers including Black Prado

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

    organization and description

    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
    ﺨ
    0.52
     tribulations
    0.46
    又は
    0.45
    থি
    0.44
    ﾖ
    0.43
    њ
    0.42
    њи
    0.42
    핑
    0.42
    форм
    0.41
     illusions
    0.41
    POSITIVE LOGITS
     항상
    0.48
    anty
    0.48
    ittees
    0.47
     පැ
    0.47
     ఎన్ని
    0.47
    ime
    0.46
     gönder
    0.46
     பள்ளி
    0.45
     पूर्णा
    0.45
     রং
    0.44
    Activations Density 0.000%

    No Known Activations