© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 15662
    Prev
    Next
    INDEX
    Explanations

    residence, bronchi, reference

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

    This neuron activates on numeric tokens, especially sequences of digits or decimal 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
     CST
    0.78
     Patri
    0.72
    קת
    0.66
    यी
    0.64
     contient
    0.64
    Diet
    0.63
    🪁
    0.61
     Caitlin
    0.61
    ন
    0.61
    ㅋㅋㅋㅋㅋㅋㅋㅋ
    0.60
    POSITIVE LOGITS
    ة
    1.00
    romptu
    0.89
    )",
    0.88
     anderer
    0.88
     dość
    0.88
    谔
    0.86
     emoción
    0.85
    )。
    0.84
    otard
    0.83
     aturan
    0.83
    Activations Density 0.004%

    No Known Activations