© 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. 202380
    Prev
    Next
    INDEX
    Explanations

    company, business, or personal mention

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

    future questions and polls

    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
     Verst
    0.48
     strangle
    0.46
    
    0.46
    యో
    0.46
     vlá
    0.46
     vyb
    0.46
     Urb
    0.45
    厈
    0.45
    ——
    0.45
    ”;
    0.44
    POSITIVE LOGITS
     ایل
    0.46
    toll
    0.44
    radar
    0.44
     каждого
    0.44
     nomm
    0.44
    emoji
    0.43
     व्हाट
    0.43
    дым
    0.42
    Ya
    0.42
     conoz
    0.42
    Activations Density 0.000%

    No Known Activations