© 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. 24-GEMMASCOPE-2-RES-16K
    7. 12019
    Prev
    Next
    INDEX
    Explanations

    leave without pay kg loss

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

    This neuron detects code-like tokens and programming identifiers (e.g. bracketed attributes, namespaces, class or method names, and other CamelCase or symbol-rich code elements).

    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_24_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
     Gently
    0.76
    lewati
    0.75
    ᵢ
    0.74
     tensors
    0.73
    omeres
    0.72
     它
    0.72
    ˆ‚
    0.72
    ₊
    0.72
    Neurons
    0.71
    Guys
    0.69
    POSITIVE LOGITS
    жнарод
    0.74
     perfe
    0.68
     tüm
    0.66
    สามารถ
    0.64
    SuppressWarnings
    0.64
     stigmat
    0.64
    μοσ
    0.63
     private
    0.63
    නා
    0.63
     riguard
    0.63
    Activations Density 0.055%

    No Known Activations