© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9650
    Prev
    Next
    INDEX
    Explanations

    consulting

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

    The neuron fires on the very first content word (often a small function word or adverb) at the beginning of a sentence.

    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
    d
    0.96
    د
    0.94
    in
    0.91
    casualties
    0.84
    dte
    0.84
    Corre
    0.83
    GJ
    0.83
    ب
    0.83
    zkod
    0.82
    enk
    0.81
    POSITIVE LOGITS
     mainWindow
    0.73
     peroxidase
    0.73
     फेस्टिवल
    0.72
     humidity
    0.71
     rheumatism
    0.71
     weathering
    0.71
     Persistence
    0.70
     dissociation
    0.70
     pregnancy
    0.69
     slag
    0.68
    Activations Density 0.000%

    No Known Activations