© 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. 78323
    Prev
    Next
    INDEX
    Explanations

    academic titles

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

    job titles and roles

    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
    ão
    0.46
    先生
    0.42
    同学
    0.42
    maskedTextBox
    0.41
    ਢ
    0.41
    董事长
    0.40
    ვილი
    0.39
    列車
    0.39
     Directeur
    0.38
    Tous
    0.38
    POSITIVE LOGITS
     pushedAt
    0.45
     utilisant
    0.44
     وزارة
    0.44
     Approx
    0.42
     STATUS
    0.42
     wattage
    0.42
     Status
    0.42
     begrenzt
    0.42
     തവണ
    0.41
     ©
    0.41
    Activations Density 0.053%

    No Known Activations