© 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. 58332
    Prev
    Next
    INDEX
    Explanations

    breaking down lists

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

    multicultural greetings

    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
    automobile
    0.50
    ikke
    0.43
    iv
    0.42
    ন্স
    0.39
    MLL
    0.39
    <unused1082>
    0.39
    <h4>
    0.38
    uster
    0.38
    the
    0.38
    ffiti
    0.38
    POSITIVE LOGITS
    <start_of_image>
    0.76
     લઈ
    0.45
     SMA
    0.44
    ̌
    0.44
     جمال
    0.42
     конца
    0.42
     Shalom
    0.42
     ശേഷം
    0.41
     အ
    0.41
     الار
    0.40
    Activations Density 0.109%

    No Known Activations