© 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. 4412
    Prev
    Next
    INDEX
    Explanations

    const

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

    The neuron responds to occurrences of the keyword “const” (especially in programming‐language declarations).

    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
    ه
    1.20
    𝒐
    1.14
    ю
    1.10
    zelfde
    1.08
    τε
    1.06
    ות
    1.03
    م
    1.02
    ת
    1.02
    ли
    1.01
    ला
    1.00
    POSITIVE LOGITS
    STAND
    1.16
    ných
    1.12
    ný
    1.09
     Calcul
    1.09
     mieszkań
    1.08
    ná
    1.07
    rophages
    1.05
     น่า
    1.05
     บวก
    1.05
    ᄁ
    1.05
    Activations Density 0.000%

    No Known Activations