© 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. 102947
    Prev
    Next
    INDEX
    Explanations

    #include, to use, aerial, cells

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

    The neuron fires on C/C++ source‐file boilerplate—especially comment‐header license/copyright blocks and related preprocessor directives.

    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
    phone
    -0.82
    Phone
    -0.79
     обувь
    -0.77
    oggetto
    -0.76
    lifting
    -0.76
    Segundo
    -0.75
    inject
    -0.75
    Threading
    -0.73
    LINES
    -0.73
    idents
    -0.70
    POSITIVE LOGITS
     sollten
    0.77
    Ety
    0.76
    Raja
    0.73
     stewards
    0.71
    翼
    0.69
     翼
    0.68
     例
    0.67
    collo
    0.66
    Svar
    0.65
    wijs
    0.65
    Activations Density 0.057%

    No Known Activations