© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 118771
    Prev
    Next
    INDEX
    Explanations

    preparative, investigational, approximates

    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
     ใน
    -2.80
     Various
    -2.72
     diğer
    -2.69
     Resultat
    -2.67
     “
    -2.67
     It
    -2.66
     Fifteen
    -2.53
     Detailed
    -2.52
     In
    -2.48
     ―
    -2.48
    POSITIVE LOGITS
    銩
    3.50
    ڧ
    3.27
    
    3.11
    ⑊
    3.02
    𞤢
    2.97
    銪
    2.80
    鬭
    2.77
     itſelf
    2.64
    </strong>
    2.64
    Ꮵ
    2.63
    Activations Density 0.066%

    No Known Activations