© 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. 75800
    Prev
    Next
    INDEX
    Explanations

    package deal

    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
     daarmee
    -0.84
    Detector
    -0.76
    Detection
    -0.75
     Detection
    -0.74
     meteen
    -0.73
     detector
    -0.72
     detect
    -0.71
     神戸
    -0.69
    endeu
    -0.69
     detection
    -0.69
    POSITIVE LOGITS
    collection
    0.96
     collection
    0.94
    ValueMap
    0.93
     SUMMER
    0.89
     collections
    0.83
     TRANSMISSION
    0.81
    elsif
    0.81
     ObjectParameter
    0.80
     colección
    0.78
    ellement
    0.77
    Activations Density 0.018%

    No Known Activations