© 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. 83946
    Prev
    Next
    INDEX
    Explanations

    plastic case, Q: style, About questions, Login Sign

    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
     jejich
    -1.64
     londres
    -1.56
     miliardi
    -1.52
     kwamba
    -1.52
     mieste
    -1.52
    pullover
    -1.51
    mẫu
    -1.48
     leerlingen
    -1.47
     nieuwe
    -1.45
    Otros
    -1.43
    POSITIVE LOGITS
     but
    2.06
     has
    1.84
    .
    1.45
     a
    1.41
     Ζ
    1.38
     endforeach
    1.35
    𝑙
    1.31
     N
    1.29
    canActivate
    1.26
     had
    1.25
    Activations Density 0.074%

    No Known Activations