© 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. 13226
    Prev
    Next
    INDEX
    Explanations

    driver

    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
    s
    -3.55
     '
    -2.98
    </em>
    -2.97
    ↵
    -2.84
    </h4>
    -2.63
    ]
    -2.63
    “
    -2.52
    ”
    -2.52
    n
    -2.39
    –
    -2.36
    POSITIVE LOGITS
    狆
    2.56
    
    2.41
    
    2.41
    もありますが
    2.28
     tornar
    2.23
     ajouter
    2.19
     indiquer
    2.16
    
    2.16
    幫助
    2.11
    猹
    2.11
    Activations Density 0.012%

    No Known Activations