© 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. 23730
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code snippets

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

    The neuron fires on the appearance of single‐letter mathematical identifiers (e.g. f, g, t, u) inside formula environments.

    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
     되
    -0.82
    >>();
    -0.80
     roleId
    -0.75
     permutations
    -0.74
    纏
    -0.70
     Likewise
    -0.69
    riche
    -0.69
     Still
    -0.69
     Currently
    -0.69
     ри
    -0.69
    POSITIVE LOGITS
    砣
    0.89
     लड़
    0.77
    Reconnect
    0.74
    ㄆ
    0.74
    enschappe
    0.73
    Decimal
    0.71
    стройки
    0.69
    harmonic
    0.69
    Westfalen
    0.69
    }\
    0.68
    Activations Density 0.038%

    No Known Activations