© 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. 82989
    Prev
    Next
    INDEX
    Explanations

    latex math environments

    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
    ⛵
    0.54
    ેટ
    0.52
    ({})
    0.50
     (\<
    0.48
    ।”
    0.47
    ⛴
    0.47
    ப்படுகிறது
    0.47
     Cof
    0.47
     detract
    0.46
     (<
    0.46
    POSITIVE LOGITS
     hij
    0.48
    IS
    0.46
     ornamental
    0.46
     migrants
    0.45
     whispers
    0.45
     mansions
    0.43
    j
    0.43
     الش
    0.42
     المج
    0.42
     fak
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.