© 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. 74548
    Prev
    Next
    INDEX
    Explanations

    error messages and code structures

    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
     drenaje
    -1.79
    duate
    -1.70
    zembro
    -1.64
    íba
    -1.64
     здесь
    -1.61
     свободы
    -1.59
     usual
    -1.54
    および
    -1.53
     füh
    -1.50
    スコア
    -1.47
    POSITIVE LOGITS
    7
    2.25
    ,  
    1.98
    8
    1.94
    ="
    1.88
    2
    1.82
    0
    1.80
    3
    1.70
    }
    1.66
    ार
    1.64
    涷
    1.59
    Activations Density 0.018%

    No Known Activations