© 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. 14060
    Prev
    Next
    INDEX
    Explanations

    Center, type, refers

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

    The neuron strongly activates on unusually rare or low‐frequency tokens.

    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
     amp
    0.79
     could
    0.75
    р
    0.73
     lying
    0.69
    Мне
    0.69
     indirectly
    0.66
    ↵
    0.64
     amounted
    0.64
     accounted
    0.64
     Holidays
    0.64
    POSITIVE LOGITS
    Terminology
    0.90
     Außerdem
    0.89
     أيضاً
    0.84
    Persistence
    0.83
    ేక
    0.81
    잼
    0.80
    jähr
    0.79
    HasFieldError
    0.77
    mime
    0.77
    ik
    0.76
    Activations Density 0.000%

    No Known Activations