© 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. 49927
    Prev
    Next
    INDEX
    Explanations

    configuration / config / configuration files

    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
    carrot
    -0.87
     péné
    -0.85
    cmath
    -0.81
    clutch
    -0.79
    vetrain
    -0.77
    sach
    -0.77
     médié
    -0.76
    naio
    -0.75
    RTSN
    -0.75
    sä
    -0.74
    POSITIVE LOGITS
     config
    4.13
     configuration
    3.97
    config
    3.39
     Config
    3.20
    Config
    3.19
     cfg
    2.98
    CONFIG
    2.95
     configurations
    2.89
     conf
    2.86
    cfg
    2.86
    Activations Density 0.047%

    No Known Activations