© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129340
    Prev
    Next
    INDEX
    Explanations

    boolean literals and punctuation

    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
     
    -1.98
    ↵↵
    -1.59
     that
    -1.55
     وت
    -1.41
    </b>
    -1.38
     seems
    -1.32
     ”
    -1.27
    2
    -1.27
     surprisingly
    -1.27
     Füßen
    -1.27
    POSITIVE LOGITS
     ส์
    1.99
    稣
    1.98
    铪
    1.84
    งิน
    1.80
    鼱
    1.70
    🫅
    1.70
    ⸨
    1.66
    厛
    1.66
    
    1.64
     a
    1.63
    Activations Density 0.004%

    No Known Activations