© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1604
    Prev
    Next
    INDEX
    Explanations

    formula for success or calculation

    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
    
    -1.69
    
    -1.59
    pulseira
    -1.49
    ープン
    -1.49
    ᐕ
    -1.48
    Ꮸ
    -1.48
    alties
    -1.47
    
    -1.45
    躂
    -1.43
     enfermedades
    -1.42
    POSITIVE LOGITS
     också
    1.58
     смесь
    1.55
     —
    1.52
    x
    1.46
    いら
    1.44
     ciment
    1.41
    up
    1.41
     dessutom
    1.38
     также
    1.38
     of
    1.38
    Activations Density 0.085%

    No Known Activations