© 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. 153799
    Prev
    Next
    INDEX
    Explanations

    awards or commendations

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

    list or phrase

    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
    بت
    0.52
    <0x8A>
    0.46
    <0x91>
    0.44
    唱
    0.44
    דינה
    0.43
    霓
    0.43
     {-
    0.42
    딧
    0.42
    헬
    0.42
    درسة
    0.42
    POSITIVE LOGITS
    ani
    0.57
     infine
    0.52
    ри
    0.46
     campuran
    0.46
    irte
    0.46
    "]));
    0.45
     Sin
    0.45
    りは
    0.45
    renerg
    0.44
    ared
    0.44
    Activations Density 0.000%

    No Known Activations