© 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. 156818
    Prev
    Next
    INDEX
    Explanations

    flourished over, alone enable, informal finish

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

    specialized standards

    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
     エネルギー
    0.50
     よる
    0.49
     comp
    0.49
     জল
    0.47
     改
    0.46
     特別
    0.46
     有
    0.45
     RESULTS
    0.44
     f
    0.44
     いく
    0.43
    POSITIVE LOGITS
    ونک
    0.52
    neze
    0.51
    اگر
    0.50
    selectedIndex
    0.50
    Vai
    0.49
    ுக்கு
    0.49
    atzen
    0.48
    ről
    0.48
    껏
    0.48
    Trước
    0.47
    Activations Density 0.000%

    No Known Activations