© 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. 16553
    Prev
    Next
    INDEX
    Explanations

    registered voter info or codes

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

    using list

    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
     terenie
    0.36
    题材
    0.34
     dostępne
    0.33
     această
    0.33
    ど
    0.33
     جانے
    0.32
     později
    0.32
     çox
    0.32
    ญาต
    0.32
     volontà
    0.31
    POSITIVE LOGITS
     （
    0.38
     दिखी
    0.38
    ixas
    0.35
    索引
    0.35
    。（
    0.33
     Hui
    0.33
    的其他
    0.32
     লি
    0.32
    ায়
    0.32
     Син
    0.32
    Activations Density 0.273%

    No Known Activations