© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123584
    Prev
    Next
    INDEX
    Explanations

    Yam, YAML, Yamin, Yamuna

    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
    臯
    -2.98
    嚳
    -2.97
    }
    
    -2.63
    เกง
    -2.59
    峮
    -2.59
    $
    -2.56
    anyahu
    -2.55
    篥
    -2.53
    ghalaya
    -2.52
    bebasan
    -2.44
    POSITIVE LOGITS
    s
    2.72
     
    2.56
     interplay
    2.36
    父の
    2.25
     Every
    2.11
     Каждый
    2.11
     Both
    2.09
    他对
    2.06
     Yam
    2.05
    ровании
    2.05
    Activations Density 0.006%

    No Known Activations