© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8863
    Prev
    Next
    INDEX
    Explanations

    much progress, much like, much more

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

    The neuron strongly activates on numeric tokens that represent day‐of‐month values in dates.

    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_31_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
    หาก
    0.63
    ](./
    0.60
    omy
    0.57
    ](../
    0.57
    장
    0.53
    組み
    0.52
    +](
    0.52
    werking
    0.52
    icro
    0.52
     Roach
    0.52
    POSITIVE LOGITS
     режисс
    0.62
     ఘటన
    0.58
     отдельно
    0.57
    ềm
    0.56
    事的
    0.55
    됐
    0.55
     ప్రత్యేక
    0.54
     வழக்க
    0.54
    ektir
    0.54
     പ്രത്യേക
    0.53
    Activations Density 0.002%

    No Known Activations