© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15488
    Prev
    Next
    INDEX
    Explanations

    those caveats

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

    The neuron strongly activates on the copula “is/are” and surrounding words in broad existential or summary statements (e.g. “there is something for everyone,” “these conditions are not met”).

    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
     its
    0.83
     Its
    0.71
    它的
    0.68
    Its
    0.61
    ⓘ
    0.61
     например
    0.60
     Entom
    0.60
     نب
    0.59
    哼
    0.58
     beispielsweise
    0.58
    POSITIVE LOGITS
     तीनों
    1.58
     allemaal
    1.40
     كلها
    1.36
     সবই
    1.34
    这一切
    1.31
     semuanya
    1.30
    這些
    1.26
     모두
    1.24
     перечис
    1.23
    全て
    1.20
    Activations Density 1.849%

    No Known Activations