© 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. 22-GEMMASCOPE-RES-131K
    7. 25187
    Prev
    Next
    INDEX
    Explanations

    bringing up topics

    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_22/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
    asanjo
    -1.27
    </td>
    -1.27
     terce
    -1.26
     copia
    -1.23
    ;->
    -1.22
     ""
    -1.16
     anest
    -1.16
     hura
    -1.15
     ベッド
    -1.15
    </h5>
    -1.15
    POSITIVE LOGITS
     dotyczące
    1.70
     in
    1.60
    家が
    1.59
     respald
    1.48
     questions
    1.46
     querían
    1.45
     питання
    1.44
     empezaron
    1.41
     tuvieron
    1.40
     dudas
    1.38
    Activations Density 0.027%

    No Known Activations