© 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. 112817
    Prev
    Next
    INDEX
    Explanations

    ... of .

    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
     étrange
    -2.06
    鸶
    -1.96
    dáms
    -1.85
     samochodu
    -1.84
    
    -1.79
     naszego
    -1.77
     verdaderamente
    -1.72
    岨
    -1.71
     perdre
    -1.70
     intérieure
    -1.70
    POSITIVE LOGITS
    </h3>
    1.73
     είναι
    1.72
     a
    1.70
    𝗽
    1.53
     by
    1.53
     to
    1.52
     eliminare
    1.50
     [
    1.46
     stemming
    1.46
     металла
    1.42
    Activations Density 0.216%

    No Known Activations