© 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. 12409
    Prev
    Next
    INDEX
    Explanations

    accept image input

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

    The neuron fires most strongly on rare or distinctive tokens—proper names, unusual words, and standalone numbers—i.e. low‐frequency or highly specific terms.

    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
    cs
    0.90
    г
    0.87
    k
    0.85
    3
    0.84
    2
    0.84
    r
    0.80
    0.80
    4
    0.79
    or
    0.77
    5
    0.77
    POSITIVE LOGITS
    𝘥
    0.93
     elettronica
    0.83
     уничто
    0.82
     incendio
    0.82
     вообще
    0.82
     кеңсесинде
    0.82
    𝙙
    0.81
     женщина
    0.81
     границы
    0.81
     жінок
    0.81
    Activations Density 0.000%

    No Known Activations