© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6690
    Prev
    Next
    INDEX
    Explanations

    type annotations

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

    The neuron fires on programming language type names that include numbers (e.g. Int32, UInt32, UInt8).

    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
    Ра
    0.75
    Ва
    0.74
    não
    0.70
    И
    0.70
    Ionic
    0.68
    Қ
    0.68
    số
    0.67
    there
    0.67
    ПО
    0.66
    الأ
    0.66
    POSITIVE LOGITS
    []
    1.39
    [][]
    1.31
     []
    1.10
    [][
    0.98
     [][]
    0.98
    [],
    0.97
    []>
    0.95
    [])
    0.93
    []);
    0.93
    [,]
    0.91
    Activations Density 0.006%

    No Known Activations