© 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. 67004
    Prev
    Next
    INDEX
    Explanations

    attribute assignment

    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
     any
    -1.72
     when
    -1.39
    ølge
    -1.34
     it
    -1.29
     that
    -1.28
    
    -1.25
     have
    -1.23
    깐
    -1.22
     using
    -1.19
     its
    -1.18
    POSITIVE LOGITS
    Documentary
    1.22
     hierzu
    1.20
     hermosos
    1.19
     anstatt
    1.16
     supuestamente
    1.16
     лицо
    1.16
    kowe
    1.13
     мужская
    1.13
     vosotros
    1.12
     özellikle
    1.12
    Activations Density 0.002%

    No Known Activations