© 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. 11389
    Prev
    Next
    INDEX
    Explanations

    personality traits and styles

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

    The neuron fires strongly on sentence‐level discourse markers—especially contrastive or emphatic adverbs like “However,” “Nevertheless,” “Consciously,” and similar transition 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
     सस्ता
    0.79
     किफायती
    0.77
    磧
    0.74
     новым
    0.73
     vineyards
    0.73
     cheaper
    0.72
     सस्ती
    0.72
    ançais
    0.70
    )、
    0.69
     ふ
    0.69
    POSITIVE LOGITS
    Personality
    1.06
     rasgos
    0.98
     personnalité
    0.93
    personality
    0.91
    人格
    0.91
     Personality
    0.90
     personality
    0.89
     psyk
    0.86
     personalidade
    0.86
     personalidad
    0.86
    Activations Density 0.004%

    No Known Activations