© 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. 3675
    Prev
    Next
    INDEX
    Explanations

    places and specific topics

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

    The main thing this neuron does is detect numeric tokens representing quantities—such as dates, ages, times, or other 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
     “
    1.02
     देखील
    1.02
    0.98
    /
    0.97
     (
    0.96
     "
    0.96
    (
    0.84
     creates
    0.82
     prolific
    0.81
     myös
    0.80
    POSITIVE LOGITS
     Казіно
    1.10
     あの
    1.08
     Гульнявыя
    1.05
    ۱
    1.01
    enapi
    0.98
     メール
    0.96
     ファイル
    0.91
     থানায়
    0.90
     อืม
    0.90
    oclaw
    0.89
    Activations Density 0.000%

    No Known Activations