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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 119031
    Prev
    Next
    INDEX
    Explanations

    random selection or process

    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
     when
    -1.04
    cún
    -0.93
    ود
    -0.83
     there
    -0.82
    ksessa
    -0.81
    榆
    -0.80
    NodeList
    -0.79
     בית
    -0.79
    ensivo
    -0.77
     before
    -0.75
    POSITIVE LOGITS
     random
    5.34
     randomly
    4.94
    random
    4.50
    Random
    4.16
     Random
    3.98
    随机
    3.91
     RANDOM
    3.77
    RANDOM
    3.59
    getRandom
    3.20
     getRandom
    2.97
    Activations Density 0.137%

    No Known Activations