© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 166018
    Prev
    Next
    INDEX
    Explanations

    plain objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SORT
    0.40
    (
    0.40
    ⏟
    0.39
    chehen
    0.39
    Entre
    0.39
    photo
    0.38
    （
    0.37
    リンク
    0.37
    &&
    0.37
    nlp
    0.37
    POSITIVE LOGITS
     গভীরভাবে
    0.40
     Innovative
    0.39
    ड्यू
    0.38
     Amtrak
    0.37
     ERISA
    0.37
     pemrograman
    0.37
     Purdue
    0.37
     dapibus
    0.37
     yaparak
    0.36
    詑
    0.36
    Activations Density 0.001%

    No Known Activations