© 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. 29085
    Prev
    Next
    INDEX
    Explanations

    directions and sides

    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
    </i>
    -1.98
    ;
    
    -1.98
     was
    -1.93
    蔔
    -1.92
    )
    -1.88
     vorigen
    -1.83
     aspetta
    -1.80
    		
    -1.76
    自家製
    -1.76
     також
    -1.73
    POSITIVE LOGITS
     of
    1.89
     soo
    1.88
    秩序
    1.87
     atractivos
    1.85
     espectaculares
    1.83
    頽
    1.80
     pervasive
    1.77
    靭
    1.74
    国防
    1.73
     Оста
    1.73
    Activations Density 0.001%

    No Known Activations