© 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. 8763
    Prev
    Next
    INDEX
    Explanations

    among us sus

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

    This neuron fires on words appearing at the beginnings of sentences.

    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
     entirely
    0.73
     pretty
    0.67
     Â
    0.67
     aforesaid
    0.67
     idiosyncratic
    0.67
     Cocktail
    0.65
     intermin
    0.64
     massive
    0.64
     fairly
    0.64
     Group
    0.64
    POSITIVE LOGITS
    youtu
    0.84
     ͡
    0.82
    🅱
    0.81
     metaverse
    0.79
    🥺
    0.75
    🤟
    0.75
    抖音
    0.73
    ̶
    0.72
     ২০২৩
    0.71
    ҉
    0.71
    Activations Density 0.016%

    No Known Activations