© 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. 84375
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    _____________
    -1.47
     夜景
    -1.46
    gebruik
    -1.41
    
    -1.40
    ᐳ
    -1.39
    står
    -1.38
     jadx
    -1.38
    
    -1.38
    𝑭
    -1.31
    ⚢
    -1.30
    POSITIVE LOGITS
    ?
    1.56
     now
    1.55
     is
    1.45
     also
    1.38
     so
    1.30
     kind
    1.30
    Each
    1.28
     плюс
    1.27
     there
    1.26
          
    1.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.