© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 12248
    Prev
    Next
    INDEX
    Explanations

    async def

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

    The neuron fires on content-bearing words—nouns, verbs, and adjectives—rather than on function words or punctuation.

    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
    交通
    0.83
    ﺪ
    0.82
    λα
    0.79
     সাহায্যে
    0.79
    ilación
    0.79
    精度
    0.77
    𝘴
    0.77
    アダ
    0.76
    ኵ
    0.76
    لومات
    0.75
    POSITIVE LOGITS
    NOUNC
    0.84
     defies
    0.80
    ברה
    0.78
     convoc
    0.77
     tuổi
    0.75
     জুন
    0.75
     sober
    0.75
     huit
    0.74
     episcop
    0.74
    таў
    0.74
    Activations Density 0.000%

    No Known Activations