© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14856
    Prev
    Next
    INDEX
    Explanations

    "see below" or similar phrasing

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

    The neuron activates on long numeric tokens—specifically floating-point numbers with multiple digits and a decimal.

    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
    ן
    1.36
    ن
    0.98
    おり
    0.94
    י
    0.92
     ascorbic
    0.91
     hitherto
    0.90
    ر
    0.90
     stockp
    0.89
     upholstered
    0.89
    ಳಿತ
    0.89
    POSITIVE LOGITS
    是最
    1.12
    és
    1.09
    ត្រូវបាន
    1.05
    簡單
    1.04
    ä
    1.03
    是非常
    1.01
    защи
    1.01
    是中国
    0.99
    紧急
    0.99
    是
    0.96
    Activations Density 0.030%

    No Known Activations