© 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. 371
    Prev
    Next
    INDEX
    Explanations

    numbers after comma

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

    The neuron fires on numerical tokens—dates, years, times, scores, and other multi-digit numbers.

    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
     and
    0.16
     кое
    0.13
    和
    0.13
    および
    0.13
    性和
    0.13
    โปร
    0.12
    ಲಾ
    0.12
     и
    0.12
    考え
    0.12
    、
    0.12
    POSITIVE LOGITS
     فقط
    0.17
     .=
    0.15
     einzige
    0.15
     einzigen
    0.15
     Seven
    0.15
    ᱗
    0.15
     Tonawanda
    0.14
    ensión
    0.14
     चूंकि
    0.14
    ayant
    0.14
    Activations Density 0.001%

    No Known Activations