© 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. 13735
    Prev
    Next
    INDEX
    Explanations

    plot or past with friends

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

    This neuron fires on open‐class (content) words—i.e. nouns, verbs, adjectives, etc.—and stays inactive on function/stop words.

    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
    m
    0.94
    ol
    0.89
    ম
    0.86
    us
    0.85
    .
    0.82
    mnt
    0.81
    .#
    0.80
    ens
    0.78
    ul
    0.77
    ين
    0.77
    POSITIVE LOGITS
    ્સ
    0.78
    楯
    0.77
     পুষ্প
    0.71
     capacidad
    0.70
     максимум
    0.70
     colección
    0.68
     تقری
    0.68
     स्थानांतरित
    0.68
     pleinement
    0.66
    avía
    0.66
    Activations Density 0.000%

    No Known Activations