© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 6014
    Prev
    Next
    INDEX
    Explanations

    life, dreams, release, optimize

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

    The main thing this neuron does is pick out longer, multi-syllable content words—especially abstract or thematic nouns and verbs.

    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
     ciddi
    0.94
     (
    0.93
     convivial
    0.88
    /
    0.86
     obviously
    0.84
     as
    0.83
     veldig
    0.81
     things
    0.80
     what
    0.80
     groupings
    0.79
    POSITIVE LOGITS
    HAHA
    0.84
    ُ
    0.79
    ➵
    0.78
    Hydrochloride
    0.76
    ,/*
    0.75
    НА
    0.75
    𝐸
    0.75
     únicamente
    0.74
    ௭
    0.74
    ̷
    0.73
    Activations Density 0.100%

    No Known Activations