© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11142
    Prev
    Next
    INDEX
    Explanations

    **synthesizing neural behavior**specialized domains knowledge industries travel driver

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

    This neuron activates on numeric tokens (i.e., digits or numbers) 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_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
     vẽ
    0.84
    フィール
    0.75
    }\
    0.74
    0
    0.74
    も含
    0.73
    ý
    0.73
    描
    0.73
    用
    0.72
     prv
    0.72
    大
    0.71
    POSITIVE LOGITS
    GPUs
    0.85
    Machines
    0.84
     Ката
    0.79
    Drivers
    0.76
    Bots
    0.75
     设备
    0.73
    JORDAN
    0.73
    Diabetes
    0.73
    উজ
    0.72
    Crane
    0.72
    Activations Density 0.000%

    No Known Activations