© 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. 70974
    Prev
    Next
    INDEX
    Explanations

    type checking and encoding utilities

    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
    ↵↵
    -2.88
     accustomed
    -2.19
    \
    -2.17
     thee
    -2.16
    や
    -1.91
    T
    -1.88
     revised
    -1.84
     beeind
    -1.82
     zahlreiche
    -1.81
     prized
    -1.80
    POSITIVE LOGITS
    鹮
    2.39
    
    2.05
    ⅿ
    1.98
    0
    1.97
    潆
    1.89
    ization
    1.88
    玙
    1.84
     diminutive
    1.82
    isArray
    1.82
     môžete
    1.81
    Activations Density 0.001%

    No Known Activations