© 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. 43819
    Prev
    Next
    INDEX
    Explanations

    game strategy and plays

    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
    Usually
    -1.93
    Nearly
    -1.70
    Perhaps
    -1.69
    Typically
    -1.63
    Those
    -1.63
    Unlike
    -1.62
    Even
    -1.55
     through
    -1.54
    Several
    -1.54
    During
    -1.53
    POSITIVE LOGITS
    ”？
    1.49
    ”、“
    1.43
    偷偷
    1.37
     extremely
    1.36
     '
    1.34
    
    1.33
     muestran
    1.33
     της
    1.27
     —
    1.25
     alguns
    1.24
    Activations Density 0.018%

    No Known Activations