© 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. 164421
    Prev
    Next
    INDEX
    Explanations

    Simpson, consumables, information, technology, timing

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

    dependency on

    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
    メージ
    0.49
    洗浄
    0.47
     Anthony
    0.46
    チャンス
    0.46
    ’
    0.46
    などで
    0.45
     Laval
    0.45
    amaged
    0.45
     Prince
    0.45
    🧖
    0.44
    POSITIVE LOGITS
     LPARAM
    0.47
    Sidebar
    0.47
     устанавли
    0.47
     เข
    0.46
    Submission
    0.46
    Callback
    0.46
     ชี
    0.46
    Appendix
    0.45
    Default
    0.44
     获取
    0.44
    Activations Density 0.000%

    No Known Activations