© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6551
    Prev
    Next
    INDEX
    Explanations

    multiple variations

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

    The neuron responds to words and phrases that express quantities or multiple items (e.g. “several,” “multiple,” “one,” 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
     дальше
    0.65
    ው
    0.64
    borderColor
    0.61
    Cy
    0.58
    эй
    0.58
     ఆధార
    0.58
    ዉ
    0.56
    лык
    0.56
     নেবে
    0.55
    륵
    0.54
    POSITIVE LOGITS
    複数の
    1.59
     multiple
    1.57
    multiple
    1.51
    多个
    1.45
     simult
    1.43
     Multiple
    1.42
    Multiple
    1.41
    複数
    1.41
     simultaneous
    1.40
     múltiples
    1.39
    Activations Density 0.897%

    No Known Activations