© 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. 9538
    Prev
    Next
    INDEX
    Explanations

    at least

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

    The neuron specializes in spotting numeric tokens representing quantities or measurements (including integers and decimal values).

    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
     titt
    0.70
    ]=='
    0.59
    ösung
    0.57
    橦
    0.55
    デス
    0.54
     libra
    0.54
    рг
    0.52
    РС
    0.52
    起源
    0.52
    圖
    0.52
    POSITIVE LOGITS
     <=
    2.03
    <=
    2.02
     ≤
    1.87
    ≤
    1.86
    leq
    1.49
    
    1.46
    >≤</
    1.43
    ⩽
    1.38
    不超过
    1.32
    leqslant
    1.24
    Activations Density 0.054%

    No Known Activations