© 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. 11171
    Prev
    Next
    INDEX
    Explanations

    remote work

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

    The neuron activates primarily on numeric or quantitative data (numbers, statistics, measurements) 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_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
     (
    0.96
    /
    0.86
    (
    0.80
    ק
    0.79
     (=
    0.75
     (!
    0.73
    minent
    0.72
    K
    0.72
     or
    0.70
     ("
    0.70
    POSITIVE LOGITS
     myös
    0.93
     även
    0.90
     także
    0.83
     ankaŭ
    0.82
     również
    0.81
    同様
    0.80
     weiteren
    0.80
     ebenfalls
    0.75
     ايضا
    0.75
     όχι
    0.74
    Activations Density 0.113%

    No Known Activations