© 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. 11319
    Prev
    Next
    INDEX
    Explanations

    combine physical activities

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

    The neuron is especially sensitive to strong descriptive adjectives that convey an extreme or intense quality (for example, “chaotic”).

    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
     визнача
    0.91
    นี้
    0.90
     цього
    0.89
    iranje
    0.87
     фі
    0.80
     collegamento
    0.80
    َ
    0.80
    ܀
    0.80
     کوئی
    0.80
     Ле
    0.80
    POSITIVE LOGITS
     gaps
    0.86
    ge
    0.80
     contingencies
    0.78
    בות
    0.75
     bitten
    0.73
    gebras
    0.71
    жат
    0.70
    igning
    0.70
     suk
    0.70
     mags
    0.69
    Activations Density 0.000%

    No Known Activations