© 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. 13102
    Prev
    Next
    INDEX
    Explanations

    demand and mandates

    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
     \
    -2.80
     you
    -2.22
     our
    -2.09
     on
    -1.88
     we
    -1.88
     наши
    -1.80
     it
    -1.77
    \
    -1.77
     his
    -1.73
     ‘
    -1.71
    POSITIVE LOGITS
    "
    2.17
    ίων
    1.88
    щении
    1.83
    loggen
    1.83
     花卉
    1.80
    噐
    1.80
    絰
    1.80
     culte
    1.79
    
    1.79
     a
    1.78
    Activations Density 0.057%

    No Known Activations