© 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. 97778
    Prev
    Next
    INDEX
    Explanations

    local dump

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

    internet system message Prompt relations

    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
    文章
    0.48
    的文章
    0.46
    方法
    0.44
    嫉
    0.44
    罩
    0.44
     Venture
    0.44
     igreja
    0.44
     Searches
    0.44
     ！
    0.43
     instrumento
    0.43
    POSITIVE LOGITS
    ce
    0.59
    nd
    0.57
    ng
    0.57
    ն
    0.56
    sen
    0.54
    nc
    0.53
     even
    0.51
    ceph
    0.50
    ası
    0.49
    two
    0.49
    Activations Density 0.001%

    No Known Activations