© 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. 68386
    Prev
    Next
    INDEX
    Explanations

    much followed by what is known or said

    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
    
    -1.86
    埏
    -1.81
     ſou
    -1.71
    擽
    -1.70
    Krankheitsbild
    -1.70
     防水
    -1.64
     ſtate
    -1.64
     niedersachsen
    -1.63
     手帳
    -1.61
     soooo
    -1.60
    POSITIVE LOGITS
     on
    1.81
     at
    1.73
     it
    1.69
     out
    1.61
     found
    1.56
     in
    1.48
     under
    1.44
     make
    1.43
     noticeable
    1.42
    t
    1.41
    Activations Density 0.041%

    No Known Activations