© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 13889
    Prev
    Next
    INDEX
    Explanations

    too much or too limiting

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

    The neuron specializes in picking up on “too X” constructions—that is, adverbs expressing excessiveness (e.g. “too small,” “too hard,” “too late”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     durchaus
    0.54
     puissiez
    0.53
     doubt
    0.52
     همچنین
    0.52
     वंचित
    0.51
     grim
    0.51
    acios
    0.50
    PLAT
    0.50
     unremarkable
    0.50
    皺
    0.50
    POSITIVE LOGITS
     too
    3.97
    too
    3.72
     Too
    3.61
    Too
    3.59
     TOO
    3.58
     слишком
    3.47
     terlalu
    3.39
     demasiado
    3.22
    太
    3.19
     troppo
    3.06
    Activations Density 0.607%

    No Known Activations