© 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. 166025
    Prev
    Next
    INDEX
    Explanations

    noun followed by common word/punctuation

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

    negative reply, something small, Hindi language

    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
     be
    0.48
     cuadr
    0.48
    ꯤ
    0.48
    ム
    0.47
    ¡
    0.47
    ꯦ
    0.47
     comenz
    0.46
     espí
    0.46
    
    0.46
    ᅦ
    0.46
    POSITIVE LOGITS
    routing
    0.49
    deer
    0.49
    stylesheets
    0.49
     hydrating
    0.48
    winding
    0.48
    ومی
    0.47
    myButtons
    0.47
    water
    0.46
    ppo
    0.46
    utis
    0.46
    Activations Density 0.000%

    No Known Activations