© 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. 51181
    Prev
    Next
    INDEX
    Explanations

    questions

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

    identifiable people

    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
    送信
    0.44
    I
    0.44
     HOT
    0.43
    affer
    0.42
     BELOW
    0.42
    IO
    0.41
     FROM
    0.41
     MANAGER
    0.40
     admite
    0.40
     Event
    0.40
    POSITIVE LOGITS
     μέ
    0.50
    oitte
    0.46
    诮
    0.46
    iami
    0.45
     Дмитри
    0.45
     Фургала
    0.45
     जगदीश
    0.45
     basilaires
    0.45
     خواست
    0.45
    UserModel
    0.45
    Activations Density 0.001%

    No Known Activations