© 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. 16332
    Prev
    Next
    INDEX
    Explanations

    code related syntax

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

    The neuron spikes on uncommon, content‐bearing words (i.e. infrequent or “rare” vocabulary) rather than on common function words.

    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
    1
    0.95
    0
    0.95
    G
    0.94
    2
    0.93
    EN
    0.91
    H
    0.91
    D
    0.86
    at
    0.86
    an
    0.84
    Not
    0.84
    POSITIVE LOGITS
     Jules
    0.92
     Chavez
    0.91
     Latinos
    0.86
     Appalachian
    0.84
     زن
    0.84
     Ching
    0.83
     treinamento
    0.83
     teeming
    0.82
     Sonora
    0.82
     Charlottesville
    0.81
    Activations Density 0.001%

    No Known Activations