© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10333
    Prev
    Next
    INDEX
    Explanations

    library includes

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

    This neuron fires on file‐name tokens (especially headers and libraries) identified by their extensions (e.g. “.h”, “.hpp”, “.io”, “oggz”, “.cc”, “.cpp”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ট্ট
    0.52
    Pdf
    0.52
    odge
    0.52
    améliorer
    0.52
    }\|_{
    0.51
    Svg
    0.50
    '),
    0.49
    })_{\
    0.48
     পিডিএফ
    0.48
    )_{(
    0.47
    POSITIVE LOGITS
     Genomic
    0.54
     fonctions
    0.52
    毽
    0.52
     Drugs
    0.52
     Wilderness
    0.52
     Barrel
    0.52
    functions
    0.51
     CallOptions
    0.51
     FUNCTIONS
    0.51
     ತಮ್ಮ
    0.51
    Activations Density 0.001%

    No Known Activations