© 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. 31949
    Prev
    Next
    INDEX
    Explanations

    ranking lists

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

    ranking and order

    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
     an
    0.57
     a
    0.52
     observations
    0.50
     views
    0.47
     remarks
    0.47
     sog
    0.46
     aspects
    0.46
     traversed
    0.46
    pictureBox
    0.45
     architectural
    0.45
    POSITIVE LOGITS
     전국
    0.52
    全國
    0.50
     टॉप
    0.49
    糰
    0.49
    ንሽ
    0.47
     फरवरी
    0.47
    娛樂
    0.47
    國內
    0.46
     মালা
    0.46
    音樂
    0.46
    Activations Density 0.000%

    No Known Activations