© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99826
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or phrases

    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
    ྄
    -1.80
    uspiel
    -1.73
    ᯾
    -1.70
     indiví
    -1.66
    鸶
    -1.65
    는
    -1.65
    
    -1.65
    姈
    -1.64
     PMID
    -1.63
     와
    -1.63
    POSITIVE LOGITS
    鏵
    2.00
    ↵↵
    1.74
     they
    1.60
     it
    1.52
    瑧
    1.47
     if
    1.46
    先
    1.46
    aporan
    1.43
     When
    1.41
     \
    1.35
    Activations Density 0.094%

    No Known Activations