© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60374
    Prev
    Next
    INDEX
    Explanations

    level or levels

    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
     مشکی
    -0.94
     phía
    -0.83
    plc
    -0.77
    누
    -0.76
    гант
    -0.76
    𝘿
    -0.76
    语句
    -0.75
    aringan
    -0.74
    어
    -0.73
    lons
    -0.73
    POSITIVE LOGITS
     level
    6.13
     levels
    5.63
    level
    4.44
    levels
    4.03
    Level
    3.81
     Levels
    3.80
    LEVEL
    3.70
     Level
    3.64
    Levels
    3.61
    レベル
    3.52
    Activations Density 0.157%

    No Known Activations