© 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. 7590
    Prev
    Next
    INDEX
    Explanations

    general formula

    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
    </h1>
    -1.78
     They
    -1.77
    ri
    -1.70
    zzarella
    -1.67
    ),
    -1.63
    </th>
    -1.60
    fication
    -1.59
    鼉
    -1.58
    able
    -1.55
    dade
    -1.54
    POSITIVE LOGITS
    .”
    1.89
    álise
    1.76
     medier
    1.66
     only
    1.57
    piar
    1.56
     reflexão
    1.51
     هاي
    1.50
    棪
    1.46
    alakip
    1.46
    iglesia
    1.46
    Activations Density 0.001%

    No Known Activations