© 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. 29183
    Prev
    Next
    INDEX
    Explanations

    occasion or occasionally

    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
     biografia
    -2.02
    );
    
    -1.91
    蠖
    -1.90
     смеси
    -1.88
    vedades
    -1.88
     TAMBÉM
    -1.86
     icona
    -1.84
    }$
    -1.81
     asisten
    -1.81
    
    -1.80
    POSITIVE LOGITS
    n
    2.58
    r
    2.14
    ↵↵
    2.03
    v
    1.98
     They
    1.95
    b
    1.88
    m
    1.83
     Letting
    1.76
     rumbling
    1.67
    l
    1.67
    Activations Density 0.008%

    No Known Activations