© 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. 11992
    Prev
    Next
    INDEX
    Explanations

    full or not full descriptions

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

    The neuron fires on isolated, content-bearing “keywords” (salient nouns, verbs, or numbers) in the text.

    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
     Learning
    0.73
     Social
    0.71
     Health
    0.70
    ם
    0.70
    ↵↵↵
    0.69
     Raleigh
    0.69
     Washington
    0.69
    লে
    0.68
    뿔
    0.68
    '
    0.68
    POSITIVE LOGITS
    様な
    0.90
     athlet
    0.86
    竣工
    0.84
    ૦
    0.83
    elast
    0.80
     bulat
    0.79
     algéb
    0.79
    下的
    0.78
     спор
    0.78
     negativ
    0.77
    Activations Density 0.001%

    No Known Activations