© 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. 133602
    Prev
    Next
    INDEX
    Explanations

    awards, weeks, space

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

    focusing, rate, role, enumerations, even, increasing, will, relief, repeat

    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
    we
    0.50
    _
    0.48
    h
    0.45
    ,\,
    0.43
    dots
    0.42
    xp
    0.41
    mapped
    0.40
    UIControl
    0.40
    text
    0.40
    cd
    0.40
    POSITIVE LOGITS
    锉
    0.43
     dhatu
    0.42
    诏
    0.41
     formalin
    0.40
    وس
    0.40
     denaturation
    0.40
    机遇
    0.40
    جان
    0.39
    糁
    0.39
     hydrolysis
    0.39
    Activations Density 0.001%

    No Known Activations