© 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. 16252
    Prev
    Next
    INDEX
    Explanations

    asciminib

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

    The neuron primarily activates on numeric expressions and statistical figures (e.g., percentages, counts, and other numbers) in the text.

    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
    ación
    0.88
    Selon
    0.79
    utsches
    0.76
    ifient
    0.73
    لاقي
    0.71
    fertigt
    0.71
    Ｖ
    0.71
    씌
    0.70
    gré
    0.68
    माना
    0.68
    POSITIVE LOGITS
    n
    0.92
     waffles
    0.77
     pewno
    0.75
     finns
    0.75
    人在
    0.75
    讳
    0.75
     부산
    0.74
     ஈடுப
    0.74
     Dorchester
    0.74
     وبه
    0.73
    Activations Density 0.000%

    No Known Activations