© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71982
    Prev
    Next
    INDEX
    Explanations

    * punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    感叹
    -1.85
    他没有
    -1.76
    淠
    -1.74
     pandémie
    -1.73
     destroyer
    -1.70
    ⦊
    -1.70
    蚺
    -1.67
    那时
    -1.67
     faune
    -1.66
    ть
    -1.66
    POSITIVE LOGITS
    .”
    2.44
     we
    2.19
    this
    2.11
     diese
    1.88
     criterion
    1.80
     â
    1.79
     if
    1.76
    *
    1.74
     Ã
    1.72
    на
    1.66
    Activations Density 0.141%

    No Known Activations