© 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. 10-GEMMASCOPE-RES-131K
    7. 86298
    Prev
    Next
    INDEX
    Explanations

    no standard definition or rule

    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
    少し
    -1.47
    perhaps
    -1.45
    我在
    -1.36
    Jika
    -1.34
    jika
    -1.30
    ovým
    -1.28
    ærke
    -1.28
    
    -1.27
    clearly
    -1.27
     cœur
    -1.26
    POSITIVE LOGITS
     this
    2.67
     that
    2.23
     how
    1.88
     or
    1.70
     what
    1.70
     you
    1.68
     it
    1.65
     today
    1.57
    /…
    1.56
     would
    1.46
    Activations Density 0.097%

    No Known Activations