© 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. 58348
    Prev
    Next
    INDEX
    Explanations

    legends and legendary people/things

    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
    ꜆
    -2.67
    
    -2.33
    虓
    -2.20
     incluidas
    -2.00
    ︕
    -2.00
    蘼
    -1.96
    isieren
    -1.95
     sprüche
    -1.93
    ⌵
    -1.91
    衕
    -1.91
    POSITIVE LOGITS
     of
    2.08
    '
    2.06
    A
    1.91
    .
    1.91
    </h2>
    1.88
    可惜
    1.80
    ありますが
    1.69
    だね
    1.67
     soon
    1.65
     wth
    1.63
    Activations Density 0.005%

    No Known Activations