© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70112
    Prev
    Next
    INDEX
    Explanations

    terms of use Clifford game virus

    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
    媗
    -1.95
    
    -1.86
    
    -1.78
    
    -1.75
     extremamente
    -1.75
    ⮑
    -1.73
    женская
    -1.73
    
    -1.72
     Descub
    -1.69
     cinquième
    -1.67
    POSITIVE LOGITS
     even
    3.33
     only
    2.83
     and
    2.59
     if
    2.41
    p
    2.23
    z
    2.19
    l
    2.19
     because
    2.17
    d
    2.14
     new
    2.11
    Activations Density 0.100%

    No Known Activations