© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135420
    Prev
    Next
    INDEX
    Explanations

    web links and URLs

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

    how to do something

    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
     parenchyma
    0.47
    
    0.47
    ച്ച്
    0.42
    `;
    0.42
    橑
    0.42
     centerline
    0.41
    ních
    0.41
     inputRange
    0.41
    rosophila
    0.41
    Phil
    0.41
    POSITIVE LOGITS
     Zuge
    0.45
     t
    0.43
     *}
    0.43
    0.42
    情
    0.41
     ي
    0.40
    src
    0.40
    هرب
    0.39
     ১৬
    0.38
     Đấy
    0.38
    Activations Density 0.000%

    No Known Activations