© 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. 3911
    Prev
    Next
    INDEX
    Explanations

    after certain punctuation/tokens

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

    This neuron detects high-precision numeric values (floating-point numbers) embedded 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
    UP
    0.98
    쐞
    0.81
    Inode
    0.80
    Ӏо
    0.79
    IN
    0.78
    ण
    0.77
    ே
    0.77
    да
    0.75
    ний
    0.75
    ือก
    0.75
    POSITIVE LOGITS
     Pens
    0.79
     Optimizer
    0.79
     meurt
    0.79
     Enquanto
    0.78
     Autres
    0.77
     Sons
    0.77
    त्रियों
    0.77
     mente
    0.75
     Cards
    0.74
     JOSE
    0.74
    Activations Density 0.002%

    No Known Activations