© 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. 22604
    Prev
    Next
    INDEX
    Explanations

    Entered dates

    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
    entown
    -1.89
    ſſel
    -1.76
     about
    -1.74
    quisition
    -1.72
    ergies
    -1.70
    aaaaaa
    -1.70
    3
    -1.69
    C
    -1.58
    wwww
    -1.54
    habitants
    -1.54
    POSITIVE LOGITS
     You
    1.84
    </h2>
    1.66
     innerhalb
    1.63
     There
    1.59
    صادر
    1.56
    ragamo
    1.53
    と呼ば
    1.48
    </b>
    1.46
     bästa
    1.46
    Any
    1.45
    Activations Density 0.113%

    No Known Activations