© 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. 4580
    Prev
    Next
    INDEX
    Explanations

    with, without, depending on

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

    The neuron strongly activates on large standalone numeric tokens (e.g. high-value numbers or years).

    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
    in
    1.06
    an
    1.00
    ar
    0.84
    р
    0.81
    0.79
    ur
    0.74
    pp
    0.73
    بر
    0.72
     modernize
    0.72
    一種
    0.71
    POSITIVE LOGITS
     sAlarm
    1.08
     btw
    1.01
     ͡
    1.01
    😅
    0.95
     хоть
    0.95
    🥺
    0.95
    🤭
    0.95
    😆
    0.94
    😄
    0.93
     hadc
    0.93
    Activations Density 0.080%

    No Known Activations