© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7403
    Prev
    Next
    INDEX
    Explanations

    context.Row

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

    The neuron fires on tokens that are part of object attribute or method accesses denoted by “dot” notation (e.g. `self.foo`, `order.bar`, `data._name`).

    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
     +=
    0.79
     setName
    0.77
     foreach
    0.76
     clearTimeout
    0.76
     boolean
    0.75
     setId
    0.72
     set
    0.70
     in
    0.68
     userid
    0.68
     =
    0.67
    POSITIVE LOGITS
    get
    0.88
    getCurrent
    0.87
    Get
    0.85
    getY
    0.80
    getRandom
    0.78
    getR
    0.78
    getDefault
    0.75
    ㄉ
    0.75
    getSelected
    0.75
    getC
    0.75
    Activations Density 0.003%

    No Known Activations