© 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. 34-GEMMASCOPE-RES-131K
    7. 77707
    Prev
    Next
    INDEX
    Explanations

    coding syntax and names

    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_34/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
    rawdź
    -0.79
    seasons
    -0.79
     niks
    -0.79
     aceler
    -0.77
     okazji
    -0.76
     fundada
    -0.74
     Características
    -0.72
    oarece
    -0.72
     установлен
    -0.71
     puntual
    -0.71
    POSITIVE LOGITS
     reachable
    0.88
     Mui
    0.79
    épendant
    0.79
    lard
    0.76
    \|_{\
    0.75
     Tab
    0.74
     slums
    0.74
    Tab
    0.74
    yAxis
    0.73
     Zand
    0.72
    Activations Density 0.021%

    No Known Activations