© 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. 10962
    Prev
    Next
    INDEX
    Explanations

    batch file commands or keywords

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

    The neuron activates on code annotations (tokens beginning with “@” followed by an identifier), i.e. Java-style annotation markers.

    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
     Churchill
    0.51
    킷
    0.51
     exposure
    0.50
     Symptoms
    0.49
     ہاتھوں
    0.49
    mıştır
    0.48
     homotopic
    0.48
     sorts
    0.48
     Ophthalmology
    0.48
     symptoms
    0.48
    POSITIVE LOGITS
     ধন
    0.57
     jednou
    0.55
     तिथे
    0.55
    মতো
    0.53
     @_
    0.52
    Pairs
    0.52
    эд
    0.52
     찾
    0.51
    '];?>
    0.50
    ี่
    0.50
    Activations Density 0.002%

    No Known Activations