© 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. 86650
    Prev
    Next
    INDEX
    Explanations

    business, features, gourmet, documentary, thermostats

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

    requiring skills or complexities

    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
    <0x92>
    0.50
    相应的
    0.46
     protectors
    0.46
     bội
    0.46
     khắc
    0.45
    '\
    0.44
     vigilance
    0.44
    仔细
    0.43
     предложение
    0.43
    》。
    0.43
    POSITIVE LOGITS
     Gour
    0.48
     G
    0.47
    TypeId
    0.47
    urte
    0.46
    hosting
    0.46
     Landkreis
    0.45
    gore
    0.45
    JIM
    0.45
    UserId
    0.44
    comm
    0.43
    Activations Density 0.001%

    No Known Activations