© 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. 86390
    Prev
    Next
    INDEX
    Explanations

    future, order, areas, following, turn, wish

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

    profile links

    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
    src
    0.61
    t
    0.48
    rat
    0.46
    st
    0.45
     unveils
    0.44
    lt
    0.44
     Pointer
    0.44
    th
    0.43
    ify
    0.43
    tractor
    0.43
    POSITIVE LOGITS
    IsPass
    0.51
    耶
    0.48
     事業
    0.46
    窩
    0.46
    葉
    0.46
    耂
    0.46
    窝
    0.46
    ври
    0.46
    楊
    0.46
    吳
    0.45
    Activations Density 0.002%

    No Known Activations