© 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. 4834
    Prev
    Next
    INDEX
    Explanations

    exponentiation and binomial coefficients

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

    This neuron detects high-level abstract or evaluative nouns—terms like decisions, consequences, areas, life, news—that signal conceptual or judgmental content.

    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
     et
    0.85
     w
    0.75
     S
    0.75
    1
    0.75
     AND
    0.74
     k
    0.73
    0
    0.73
     a
    0.71
     en
    0.71
     WITH
    0.71
    POSITIVE LOGITS
     bebés
    0.89
    。「
    0.88
    Então
    0.87
    。『
    0.86
     أثناء
    0.84
    。“
    0.82
     bebé
    0.82
     במהלך
    0.82
     отмечает
    0.80
    Durante
    0.79
    Activations Density 0.032%

    No Known Activations