© 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. 7617
    Prev
    Next
    INDEX
    Explanations

    "Hope this is helpful"

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

    The neuron strongly activates on standalone decimal‐number tokens (floating‐point numerals).

    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
     まず
    0.71
     (…)
    0.68
     وذلك
    0.66
     iaitu
    0.64
    économie
    0.61
    誂
    0.60
    醗
    0.60
     llega
    0.58
    iče
    0.58
     yaitu
    0.58
    POSITIVE LOGITS
    <eos>
    0.96
    끗
    0.63
     ज्यादा
    0.60
    ""
    0.59
    更多
    0.59
    अन्य
    0.58
    <0x00>
    0.55
    样子
    0.53
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.52
     शुभकामनाएं
    0.51
    Activations Density 0.260%

    No Known Activations