© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 100151
    Prev
    Next
    INDEX
    Explanations

    function calls or nesting

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

    variable access or method call

    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
    mdash
    0.45
    jm
    0.44
     satu
    0.38
     frayed
    0.38
    initialized
    0.38
    JM
    0.37
    🏾
    0.37
    has
    0.37
    extensions
    0.37
    рто
    0.37
    POSITIVE LOGITS
    立
    0.47
    為主
    0.45
    צוע
    0.43
    rzez
    0.42
    ״
    0.38
    ،
    0.38
    劉
    0.37
    的产品
    0.37
    atief
    0.37
     milieux
    0.37
    Activations Density 0.002%

    No Known Activations