© 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. 16072
    Prev
    Next
    INDEX
    Explanations

    brown hair

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

    lists and categories

    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
     veya
    0.59
     hoặc
    0.59
     alebo
    0.56
     或
    0.55
     or
    0.54
     või
    0.52
    或其他
    0.52
    หรือ
    0.52
    或
    0.52
     или
    0.52
    POSITIVE LOGITS
    with
    0.99
     disertai
    0.96
     accompanied
    0.95
     accompagné
    0.93
    且
    0.93
     avec
    0.92
     עם
    0.91
    とその
    0.91
    accompanied
    0.91
     with
    0.91
    Activations Density 0.115%

    No Known Activations