© 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. 84922
    Prev
    Next
    INDEX
    Explanations

    code file paths and technical terms

    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
     soldadura
    -1.77
     cómoda
    -1.67
     financiación
    -1.65
     exportación
    -1.64
     their
    -1.59
     automóviles
    -1.58
     gastronomía
    -1.57
     drenaje
    -1.55
     raíz
    -1.55
     cerámica
    -1.52
    POSITIVE LOGITS
     брюки
    1.53
     in
    1.46
    if
    1.39
    Beschrijving
    1.38
    ЛИ
    1.35
     vedere
    1.34
    lograph
    1.34
    Если
    1.34
     but
    1.32
    település
    1.31
    Activations Density 0.005%

    No Known Activations