© 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. 4489
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on code identifiers for function or method calls (e.g. API or library routines followed by “()”).

    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
    Ἠ
    0.64
    ‌هایی
    0.63
     экономической
    0.62
    Ἐ
    0.62
    ইয়া
    0.61
     ближе
    0.59
    
    0.59
    íoch
    0.57
    प्टेंबर
    0.55
    ปัจ
    0.55
    POSITIVE LOGITS
     কথাও
    0.63
     remark
    0.59
     লোকদের
    0.59
     get
    0.58
    abul
    0.58
     બનાવ
    0.57
     sentences
    0.57
    (_
    0.56
    "",
    0.56
    ″
    0.56
    Activations Density 0.005%

    No Known Activations