© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66296
    Prev
    Next
    INDEX
    Explanations

    proper nouns and technical terms

    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
     those
    -1.23
     their
    -1.12
     miljoen
    -1.11
     that
    -1.11
     Those
    -0.98
    vespa
    -0.98
    AutoScaleMode
    -0.97
     of
    -0.95
    上角
    -0.94
    
    -0.93
    POSITIVE LOGITS
    Zusammenfassung
    1.12
    ariConfig
    1.12
    Medien
    1.08
    HISTORIA
    1.05
    תוך
    1.01
    Especificaciones
    1.01
    刻意
    1.00
    Setiap
    0.98
     primary
    0.98
    のよ
    0.98
    Activations Density 0.014%

    No Known Activations