© 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. 2426
    Prev
    Next
    INDEX
    Explanations

    I explanation

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

    The neuron strongly activates on large numeric tokens (especially four‐digit or higher numbers, often with decimal points).

    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
     ד
    0.94
     라고
    0.88
    說是
    0.84
     scritta
    0.83
     surprising
    0.82
     constitutes
    0.82
     ώστε
    0.81
     disting
    0.80
     remarkable
    0.80
     Suggest
    0.79
    POSITIVE LOGITS
    ع
    1.06
    슨
    0.96
    ست
    0.95
    НЫ
    0.93
    ش
    0.93
    ند
    0.91
     arbres
    0.90
    сыз
    0.88
    ならない
    0.88
     усі
    0.88
    Activations Density 0.018%

    No Known Activations