© 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. 14718
    Prev
    Next
    INDEX
    Explanations

    types of lists

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

    The neuron fires on plural count nouns—concrete items or units that are typically quantified (e.g. “panels,” “sets,” “bags,” “plants,” “counts,” “quotes,” etc.).

    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
    意味着
    0.52
    这一点
    0.51
    ട്ടില്ല
    0.50
    涯
    0.50
    此同时
    0.48
     концу
    0.48
    sieh
    0.47
    стане
    0.47
    idimensional
    0.46
    彼の
    0.46
    POSITIVE LOGITS
     varios
    0.57
     ரா
    0.56
     של
    0.55
     ג
    0.54
     נ
    0.54
     concatenate
    0.54
     fico
    0.53
     DE
    0.53
     plusieurs
    0.53
     ט
    0.52
    Activations Density 0.000%

    No Known Activations