© 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. 87157
    Prev
    Next
    INDEX
    Explanations

    binary bit representation

    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
    附近
    -0.77
    больше
    -0.75
    ensible
    -0.74
    茸
    -0.70
    JWT
    -0.69
    秋天
    -0.69
     perks
    -0.67
    夏天
    -0.66
    leiter
    -0.66
     surfaces
    -0.65
    POSITIVE LOGITS
     LSB
    2.34
     Least
    2.00
     MS
    2.00
    Least
    1.96
     least
    1.93
    MSB
    1.91
     lower
    1.87
    LSB
    1.84
     high
    1.59
     lowest
    1.56
    Activations Density 0.055%

    No Known Activations