© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15217
    Prev
    Next
    INDEX
    Explanations

    country names, settle in, trust

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

    The neuron fires most strongly on relatively rare, content-heavy words (i.e. high-information nouns, verbs, and adjectives) rather than on common function words.

    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
    <0x18>
    0.57
    ⑷
    0.55
    Corruption
    0.54
    Sup
    0.54
    ,
    0.54
    COR
    0.52
    >/
    0.52
    Suppress
    0.51
    <(),
    0.50
    Timber
    0.50
    POSITIVE LOGITS
    icular
    0.72
     చర్చ
    0.67
    ラル
    0.64
     районы
    0.64
     രീതി
    0.63
    тесь
    0.61
    ビング
    0.57
    ляет
    0.57
    入口
    0.57
    ချင်း
    0.57
    Activations Density 0.001%

    No Known Activations