© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 50500
    Prev
    Next
    INDEX
    Explanations

    configuration properties

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

    This neuron fires on technical identifiers in code—module, package, or library names (and related path or import segments).

    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
    ोड़
    -0.94
     trato
    -0.94
     говорить
    -0.85
     група
    -0.84
    釧
    -0.82
     처리
    -0.81
    家は
    -0.81
     Economía
    -0.81
     though
    -0.80
    ACIO
    -0.80
    POSITIVE LOGITS
    junit
    0.84
     amet
    0.82
    context
    0.79
     aspiration
    0.77
    ган
    0.76
    امل
    0.75
    گي
    0.75
    人民共和国
    0.74
    rž
    0.74
     nici
    0.74
    Activations Density 0.004%

    No Known Activations