© 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. 67961
    Prev
    Next
    INDEX
    Explanations

    education or business contexts

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

    certainly course spy sure who

    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
    Negative Logits
     كانت
    0.48
    ك
    0.46
     magnification
    0.42
     shields
    0.42
     tienda
    0.42
     নিজেদের
    0.40
     +\
    0.40
     곧
    0.40
     بعض
    0.39
     quelques
    0.38
    POSITIVE LOGITS
    情報を
    0.54
    information
    0.52
    情報は
    0.52
    Chaer
    0.50
    数の
    0.48
    チャンネル
    0.48
    yester
    0.48
    連絡
    0.48
    ེད་
    0.48
    headlines
    0.47
    Activations Density 0.000%

    No Known Activations