© 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. 7196
    Prev
    Next
    INDEX
    Explanations

    conquering complexity or belief

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

    This neuron detects positive evaluative adjectives used in promotional or testimonial language (e.g. trusted, educational, informative, revealing, fun, healthy, tips).

    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
     martingale
    0.75
    쩌
    0.75
     polynom
    0.73
    폭
    0.69
    ные
    0.69
     tailings
    0.66
    ↼
    0.65
     filtered
    0.64
    쿠
    0.63
    polygon
    0.63
    POSITIVE LOGITS
    𝗕
    0.89
     esclusivamente
    0.86
     hizo
    0.84
     sentimiento
    0.82
    お金
    0.82
    कृपया
    0.81
     entrambi
    0.81
     Kindergarten
    0.81
     espes
    0.81
     Ukraine
    0.80
    Activations Density 0.001%

    No Known Activations