© 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. 45493
    Prev
    Next
    INDEX
    Explanations

    programming and specialized fields

    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
    
    -1.75
    </i>
    -1.70
    5
    -1.66
    7
    -1.63
    1
    -1.59
    ization
    -1.57
    6
    -1.53
     первой
    -1.51
     Begründung
    -1.50
    8
    -1.48
    POSITIVE LOGITS
    </sup>
    1.81
    ́ng
    1.75
    ısında
    1.74
    the
    1.73
    </h2>
    1.70
    </h4>
    1.70
    he
    1.69
    峮
    1.64
    雰
    1.63
    '])){
    1.62
    Activations Density 0.001%

    No Known Activations