© 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. 64482
    Prev
    Next
    INDEX
    Explanations

    lists of items or names

    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
    Negative Logits
     either
    -1.16
     then
    -1.11
    either
    -1.10
    đen
    -1.09
     ὅ
    -1.08
     specifically
    -1.06
     οὐ
    -1.05
     בנושא
    -1.05
    (*^^*)
    -1.05
     rodillas
    -1.02
    POSITIVE LOGITS
     many
    1.29
     among
    1.20
     العديد
    1.18
     numerous
    1.13
    Among
    1.10
     многих
    1.08
    Many
    1.05
     många
    1.04
     vieler
    1.03
    給你
    1.02
    Activations Density 0.046%

    No Known Activations