© 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. 98844
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns and technical terms

    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
    Negative Logits
    簠
    -3.08
    鶿
    -3.05
    
    -2.91
    ౧
    -2.80
     nových
    -2.67
    ată
    -2.59
    氿
    -2.59
    ᥀
    -2.58
    がとても
    -2.52
    珰
    -2.52
    POSITIVE LOGITS
    It
    3.06
    While
    2.77
     It
    2.69
    Interestingly
    2.55
    After
    2.55
    One
    2.53
     Because
    2.50
    ;
    2.45
    Despite
    2.41
    Among
    2.41
    Activations Density 0.006%

    No Known Activations