© 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. 64592
    Prev
    Next
    INDEX
    Explanations

    code snippets and commands

    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
    pañol
    -1.00
    WritableDatabase
    -0.94
     افزار
    -0.92
     Infrastruktur
    -0.88
     også
    -0.88
    əsi
    -0.88
    ünk
    -0.88
    chrift
    -0.87
    шена
    -0.85
     também
    -0.84
    POSITIVE LOGITS
     to
    1.20
    少なく
    0.98
    igsaw
    0.96
     sondern
    0.95
    Excessive
    0.92
        
    0.91
    前後
    0.91
     condem
    0.90
    Anywhere
    0.90
     सिस्ट
    0.88
    Activations Density 0.010%

    No Known Activations