© 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. 68477
    Prev
    Next
    INDEX
    Explanations

    information labels

    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
    𖣘
    -1.44
    핌
    -1.38
     ive
    -1.36
    お疲れ様でした
    -1.34
     reprend
    -1.32
     innumerable
    -1.30
    Like
    -1.29
     nochmals
    -1.28
     therefore
    -1.27
     unangemessene
    -1.27
    POSITIVE LOGITS
     and
    2.17
     logis
    1.21
    ⅹ
    1.18
    comfortable
    1.17
     herbes
    1.16
    assertIs
    1.16
    াম
    1.15
    
    1.15
     концеп
    1.13
     fers
    1.13
    Activations Density 0.033%

    No Known Activations