© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6586
    Prev
    Next
    INDEX
    Explanations

    numbers and links

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

    The neuron strongly activates on relatively uncommon, information-rich content words (rather than frequent function words).

    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_31_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
     주장
    0.73
     ಹಲವಾರು
    0.69
     পাশ্চাত্য
    0.69
     اغ
    0.68
    ה
    0.67
     Το
    0.66
     Эти
    0.66
     diverge
    0.65
    ℅
    0.64
     هذ
    0.63
    POSITIVE LOGITS
    ,((
    0.98
    ,(
    0.86
     sawmill
    0.86
     trafik
    0.84
    rosophila
    0.78
     tersedia
    0.75
     chainsaw
    0.75
     scorsa
    0.75
    एनएल
    0.74
    റ്റർ
    0.74
    Activations Density 0.000%

    No Known Activations