© 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. 10-GEMMASCOPE-RES-131K
    7. 68263
    Prev
    Next
    INDEX
    Explanations

    languages and technical contexts

    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_10/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
    谖
    -3.05
     nahil
    -2.81
     zitate
    -2.48
    ܆
    -2.44
    箆
    -2.41
    
    -2.39
     hodnot
    -2.38
     supposed
    -2.36
    
    -2.33
    等于
    -2.31
    POSITIVE LOGITS
    ’
    2.86
    </h2>
    2.80
    (
    2.39
     vandaag
    2.31
    此事
    2.27
     Many
    2.23
    
    2.20
     “
    2.14
    térature
    2.14
    鸶
    2.13
    Activations Density 0.001%

    No Known Activations