© 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. 65176
    Prev
    Next
    INDEX
    Explanations

    "palsy", "batsman", "Pty Ltd"

    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
    疍
    -2.98
    賡
    -2.84
    
    -2.70
    迳
    -2.66
    d
    -2.66
    贗
    -2.61
    s
    -2.56
    忉
    -2.53
     ⓒ
    -2.45
    '
    -2.45
    POSITIVE LOGITS
     
    2.89
     neuen
    2.83
     richtige
    2.73
    I
    2.73
     kinda
    2.50
     Difficult
    2.45
    They
    2.42
    蓠
    2.34
     ......
    2.34
     mümkün
    2.33
    Activations Density 0.002%

    No Known Activations