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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91841
    Prev
    Next
    INDEX
    Explanations

    extracting information and features

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron responds to technical terms describing statistical modeling of data—e.g. words about capturing, mining, distributions, learned features, and related quantitative concepts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     faſt
    -0.99
     matériel
    -0.92
    PointerException
    -0.91
     negativ
    -0.87
    iniz
    -0.83
    hte
    -0.82
    ylo
    -0.81
    ArrayAdapter
    -0.79
    integer
    -0.79
     technologie
    -0.78
    POSITIVE LOGITS
     information
    1.84
     relationships
    1.58
     relations
    1.31
     Information
    1.29
     patterns
    1.27
     useful
    1.23
     features
    1.19
     structure
    1.17
     relationship
    1.17
     meaningful
    1.13
    Activations Density 0.122%

    No Known Activations