© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7322
    Prev
    Next
    INDEX
    Explanations

    potential problems

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

    This neuron highlights the single most distinctive or content-rich word in each text segment.

    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
     presentó
    0.66
    ō
    0.62
     fermion
    0.61
     Geophys
    0.60
     nécessite
    0.59
    َي
    0.59
     voulait
    0.59
     বরাত
    0.59
     RO
    0.58
     LGBTQ
    0.58
    POSITIVE LOGITS
     zprac
    0.86
    胫
    0.86
    ﺨ
    0.86
     beauties
    0.84
    FromThe
    0.82
     seh
    0.81
     формы
    0.80
    Promises
    0.80
    ა
    0.79
     baddies
    0.78
    Activations Density 0.000%

    No Known Activations