© 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. 69065
    Prev
    Next
    INDEX
    Explanations

    09 followed by colon

    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
    </
    -2.25
    檸
    -2.11
    ﺶ
    -2.09
    ,  
    -2.08
     They
    -2.08
    
    -2.05
     Apakah
    -2.02
     Including
    -2.00
    ropractic
    -1.99
     Notwithstanding
    -1.98
    POSITIVE LOGITS
    \
    2.63
    1
    2.33
    苙
    2.20
     ‘‘
    2.14
    ↵
    2.13
    他会
    2.09
    ‘
    1.98
    即便是
    1.95
    餵
    1.95
    .“
    1.90
    Activations Density 0.046%

    No Known Activations