© 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. 206812
    Prev
    Next
    INDEX
    Explanations

    cub, St, appliances, enough, quick, past, with

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

    specifying AI purpose

    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
    月の
    0.55
    UpdateRequest
    0.52
    ুর
    0.48
    参赛
    0.48
    еру
    0.48
    㴼
    0.48
    相比
    0.47
    ਡ
    0.46
    最多
    0.46
    月から
    0.46
    POSITIVE LOGITS
     ((
    0.54
     (
    0.51
     te
    0.46
     Coronation
    0.46
     indors
    0.44
     llamada
    0.44
     ؛
    0.43
     '(
    0.42
     ("
    0.42
     Railway
    0.42
    Activations Density 0.000%

    No Known Activations