© 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. 10001
    Prev
    Next
    INDEX
    Explanations

    assessment of or appeals

    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
    2
    -3.94
    8
    -3.52
    眼睛
    -3.09
    在我
    -3.00
    鬭
    -2.91
    5
    -2.81
    多
    -2.73
    c
    -2.66
    1
    -2.59
     решили
    -2.56
    POSITIVE LOGITS
    鄠
    3.52
    汭
    3.38
    
    3.33
    閎
    3.31
    ikusbot
    3.19
    箩
    3.16
    灕
    3.06
    玕
    3.05
     of
    2.97
    箆
    2.83
    Activations Density 0.011%

    No Known Activations