© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15167
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

    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
     at
    -1.54
     When
    -1.52
     for
    -1.52
     Since
    -1.50
     that
    -1.50
     There
    -1.49
     from
    -1.45
     ....
    -1.45
     As
    -1.41
     only
    -1.39
    POSITIVE LOGITS
    鉏
    1.46
     baumwolle
    1.41
     BEN
    1.40
     frança
    1.38
    鹪
    1.38
     niedersachsen
    1.38
     luy
    1.32
    
    1.29
     heo
    1.27
    
    1.26
    Activations Density 0.027%

    No Known Activations