© 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. 122558
    Prev
    Next
    INDEX
    Explanations

    officer, pay, Linda, email

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

    definition, root, instance

    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
    G
    0.69
    D
    0.62
    S
    0.59
    P
    0.59
    R
    0.55
    Y
    0.55
    M
    0.53
    V
    0.52
    N
    0.49
    T
    0.49
    POSITIVE LOGITS
     شیطان
    0.54
    ისუფ
    0.54
     schlecht
    0.50
     საშუალ
    0.50
     ashamed
    0.49
    wości
    0.47
     bewildered
    0.47
     সীমিত
    0.47
     предпоч
    0.47
     キッチン
    0.47
    Activations Density 0.003%

    No Known Activations