© 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. 8922
    Prev
    Next
    INDEX
    Explanations

    diagnostic imaging

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

    The neuron fires strongly on uncommon, low‐frequency vocabulary items (especially long or irregular 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
    Kent
    0.64
    gill
    0.64
    ža
    0.62
    ▫
    0.62
    doll
    0.61
    aglio
    0.61
    McK
    0.61
    ९
    0.61
    KOH
    0.60
    يته
    0.60
    POSITIVE LOGITS
     virial
    0.79
     lakukan
    0.78
    eonium
    0.77
     bustling
    0.77
     Duma
    0.77
     Sitio
    0.75
     workings
    0.75
     Tolstoy
    0.75
    enciones
    0.75
    "]},
    0.75
    Activations Density 0.001%

    No Known Activations