© 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. 127712
    Prev
    Next
    INDEX
    Explanations

    so I

    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
     таких
    -1.11
    cestry
    -1.01
     atyp
    -0.95
    entlich
    -0.94
    พาะ
    -0.93
    因為
    -0.92
    🎇
    -0.92
    咁
    -0.90
    öffnung
    -0.90
        
    -0.90
    POSITIVE LOGITS
     suggest
    1.55
     suggesting
    1.47
     suggests
    1.46
     clearly
    1.30
     believe
    1.30
     indicates
    1.25
     it
    1.24
     likely
    1.20
     know
    1.19
     perhaps
    1.19
    Activations Density 0.044%

    No Known Activations