© 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. 16445
    Prev
    Next
    INDEX
    Explanations

    high quality, frequency, or performance

    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
      
    -3.34
     “
    -3.16
    <
    -2.77
    ↵↵
    -2.67
          
    -2.61
    >
    -2.52
     (“
    -2.50
    ,”
    -2.36
    ']>
    -2.30
     эффектив
    -2.22
    POSITIVE LOGITS
    s
    2.75
    ченные
    2.73
    providedIn
    2.63
     miliardi
    2.52
    kunjung
    2.52
     menatap
    2.48
     problemen
    2.47
    "]:
    2.44
    gezogen
    2.44
    Comté
    2.41
    Activations Density 0.090%

    No Known Activations