© 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. 100512
    Prev
    Next
    INDEX
    Explanations

    foreign language snippets

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

    patches, blocks, fundamentals, string, CSV

    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
    '></
    0.51
    のマ
    0.49
     Sebagai
    0.48
    推薦
    0.48
     ಜೀವನ
    0.47
     یونیورسٹی
    0.46
     ಇದಕ್ಕೆ
    0.46
    corsi
    0.46
    لین
    0.45
    噺
    0.45
    POSITIVE LOGITS
    ips
    0.45
    enez
    0.44
    ené
    0.44
    ified
    0.44
    rás
    0.43
    áp
    0.43
    வில
    0.42
    imme
    0.42
    ile
    0.42
    ebug
    0.41
    Activations Density 0.000%

    No Known Activations