© 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. 27886
    Prev
    Next
    INDEX
    Explanations

    fashion and style

    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
     ponieważ
    -1.22
    買って
    -1.13
     from
    -1.09
    
    -1.07
     untuk
    -1.03
     mentioned
    -1.02
    s
    -1.02
    Добрый
    -1.02
     supported
    -1.01
     Hogar
    -1.01
    POSITIVE LOGITS
     fashion
    1.75
     Fashion
    1.41
    Fashion
    1.40
    不
    1.32
    страция
    1.23
     styling
    1.23
     नए
    1.23
     年轻
    1.22
     Nairobi
    1.21
    穑
    1.20
    Activations Density 0.059%

    No Known Activations