© 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. 120958
    Prev
    Next
    INDEX
    Explanations

    final reminder

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

    writing scene descriptions

    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
    निश्ड
    0.59
     문제입니다
    0.49
    なければ
    0.49
    点は
    0.49
    itating
    0.49
    漬
    0.48
    िस
    0.48
    濃度
    0.48
    તી
    0.47
     শুক
    0.47
    POSITIVE LOGITS
    Space
    0.62
    DEL
    0.61
    word
    0.55
    Cruise
    0.52
     espace
    0.51
    space
    0.51
    DR
    0.50
    app
    0.50
     Lounge
    0.50
     Space
    0.50
    Activations Density 0.001%

    No Known Activations