© 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. 32838
    Prev
    Next
    INDEX
    Explanations

    Jim followed by another name

    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
     
    -2.75
    <em>
    -2.59
     sparking
    -2.31
     $
    -2.23
    and
    -2.16
     ebenso
    -2.08
    写真の
    -2.03
     manchmal
    -1.95
     schnellen
    -1.92
    についての
    -1.91
    POSITIVE LOGITS
    佧
    2.73
    喼
    2.69
     reager
    2.59
    
    2.39
     rajut
    2.27
    鉏
    2.25
     edile
    2.22
     kemer
    2.22
     huden
    2.20
     westfalen
    2.17
    Activations Density 0.083%

    No Known Activations