© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 94017
    Prev
    Next
    INDEX
    Explanations

    mapRoute or mapGroups

    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
    そこで
    -0.75
     Dicht
    -0.71
    惆
    -0.68
    बल
    -0.68
    勸
    -0.68
     인
    -0.67
     Hospitals
    -0.66
    鐺
    -0.66
    imdb
    -0.65
    River
    -0.65
    POSITIVE LOGITS
     DMX
    0.79
    $(-
    0.72
    nią
    0.68
     reflexion
    0.67
     $[-
    0.67
     feeders
    0.66
    κης
    0.66
    Максим
    0.66
    ISTA
    0.65
     EGL
    0.65
    Activations Density 0.049%

    No Known Activations