© 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. 10-GEMMASCOPE-RES-131K
    4. 61382
    Prev
    Next
    INDEX
    Explanations

    programming libraries

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

    The neuron detects module path components (directory names like “lib”, “core”, “extensions”, etc.) in import/require statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     beliebtesten
    -1.60
     for
    -1.59
     complimented
    -1.34
     in
    -1.34
     participado
    -1.28
     bestens
    -1.27
     детская
    -1.24
     verur
    -1.24
    案例
    -1.23
     तु
    -1.22
    POSITIVE LOGITS
    ми
    1.52
     anadolu
    1.48
    istungen
    1.44
     JOSÉ
    1.38
     SHIN
    1.36
     españa
    1.36
     Calcio
    1.35
    纤
    1.33
    っしゃ
    1.33
    mathrm
    1.33
    Activations Density 0.060%

    No Known Activations