© 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. 12476
    Prev
    Next
    INDEX
    Explanations

    instructions for action

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

    The neuron is essentially detecting unusually rare or “high‐index” tokens—i.e. low‐frequency or outlying words in the vocabulary.

    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
    $
    0.83
     Microscope
    0.68
    Discrete
    0.66
     阅读全文
    0.64
    "<
    0.62
    $~
    0.60
    $.\
    0.59
    {$
    0.59
     dtype
    0.57
     =-
    0.56
    POSITIVE LOGITS
     henna
    1.16
    lav
    1.07
     minivan
    0.99
     cafeteria
    0.97
     hatchery
    0.95
     часы
    0.95
     abr
    0.93
     камеры
    0.92
     ideia
    0.92
     lau
    0.91
    Activations Density 0.000%

    No Known Activations