© 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. 16110
    Prev
    Next
    INDEX
    Explanations

    other words or meanings

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

    The neuron is looking for content words that express relationships or linkage between ideas—particularly terms of accompaniment or contrast (e.g. “accompanied,” “alongside,” “opposite”).

    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
     pode
    0.68
    :.
    0.68
    :_
    0.66
    flies
    0.66
    *:
    0.64
    missions
    0.63
    CATS
    0.63
    inhos
    0.63
    ৫
    0.62
    ła
    0.61
    POSITIVE LOGITS
    相应的
    0.79
     경우가
    0.73
    其他
    0.70
     పాటు
    0.70
    alakip
    0.70
     다른
    0.69
     создание
    0.69
    ことも
    0.68
    การ
    0.68
    वेलकम
    0.68
    Activations Density 0.613%

    No Known Activations