© 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. 113037
    Prev
    Next
    INDEX
    Explanations

    fruitful, productive, rewarding outcomes

    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
    
    -1.90
    ка
    -1.82
    </h1>
    -1.80
    "}}
    -1.77
    charCodeAt
    -1.73
    蟊
    -1.67
    ں
    -1.66
     gurus
    -1.64
    谂
    -1.62
    </i>
    -1.57
    POSITIVE LOGITS
    </em>
    2.11
     Not
    1.78
    which
    1.77
    不过是
    1.70
     However
    1.65
     fruitful
    1.62
     setelah
    1.62
     Which
    1.59
     siguientes
    1.57
     
    1.54
    Activations Density 0.014%

    No Known Activations