© 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. 59199
    Prev
    Next
    INDEX
    Explanations

    rate or amount per unit

    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
    佉
    -1.66
    derdag
    -1.60
    }>
    -1.60
    etsk
    -1.56
     tačiau
    -1.48
     niekoľ
    -1.48
     fondé
    -1.46
    sibilidad
    -1.44
     nových
    -1.44
     niezbęd
    -1.41
    POSITIVE LOGITS
    '
    1.57
    та
    1.52
    Traduction
    1.50
    ↵
    1.49
    شون
    1.47
    Usually
    1.31
     prosi
    1.29
     if
    1.28
     çantası
    1.28
    Système
    1.27
    Activations Density 0.010%

    No Known Activations