© 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. 10999
    Prev
    Next
    INDEX
    Explanations

    gear shifting control

    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
    읗
    -1.82
    s
    -1.81
     travailleurs
    -1.78
    隐隐
    -1.77
     of
    -1.67
    as
    -1.66
     œufs
    -1.63
     dirigeants
    -1.60
     tiefen
    -1.60
     milliers
    -1.58
    POSITIVE LOGITS
    嫫
    1.89
     réus
    1.78
    迓
    1.66
    ！"
    1.65
     guma
    1.61
     Spanien
    1.61
    揶
    1.59
     телефона
    1.55
     szczeg
    1.54
    同伴
    1.54
    Activations Density 0.007%

    No Known Activations