© 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. 6238
    Prev
    Next
    INDEX
    Explanations

    describing adjectives and adverbs

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

    This neuron responds to uncommon or distinctive content 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
    การณ์
    0.59
     നിങ്ങൾക്ക്
    0.59
     \
    0.57
     கூறப்படுகிறது
    0.57
    以及
    0.57
    які
    0.55
    дання
    0.54
     tendrás
    0.54
     ,\
    0.53
     :\
    0.52
    POSITIVE LOGITS
    ly
    1.37
    istically
    1.28
    ingly
    1.19
    ially
    1.16
    ishly
    1.09
    aneously
    1.09
     enough
    1.06
    ively
    1.05
    ently
    1.04
    antly
    1.04
    Activations Density 0.440%

    No Known Activations