© 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. 10477
    Prev
    Next
    INDEX
    Explanations

    ordinary people and AI

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

    The neuron is essentially detecting very high‐frequency, low‐information “function” words (common stopwords and adverbs).

    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
    Ф
    0.86
    𝕦
    0.83
    우
    0.79
    Υ
    0.79
    𝕤
    0.76
    1
    0.76
    у
    0.75
    М
    0.75
    fetchall
    0.74
    아
    0.74
    POSITIVE LOGITS
     pundits
    1.00
     bushing
    0.85
     perils
    0.84
     nightlife
    0.84
     resurgence
    0.83
     renov
    0.81
     refurbishment
    0.81
     bores
    0.81
     bushings
    0.81
     photocurrent
    0.81
    Activations Density 0.000%

    No Known Activations