© 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. 12336
    Prev
    Next
    INDEX
    Explanations

    social commentary and complex themes

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

    This neuron fires on prominent content nouns that name the topic under discussion (e.g. bitcoin, cryptocurrency, electronics, insects).

    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
    .
    0.74
     commands
    0.64
     reacting
    0.64
     swoją
    0.63
    François
    0.63
    -
    0.61
    .<
    0.61
    .-
    0.61
     ομά
    0.61
    ®.
    0.61
    POSITIVE LOGITS
    никам
    0.74
    hamdulillah
    0.74
    了我
    0.70
     Erfolg
    0.67
     ghee
    0.67
    ナス
    0.67
     Saving
    0.66
     ಇದೆ
    0.65
    カイブ
    0.65
     Waalaikumsalam
    0.65
    Activations Density 0.572%

    No Known Activations