© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3416
    Prev
    Next
    INDEX
    Explanations

    words introducing contrast or consequence

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

    This neuron primarily responds to numeric tokens (numbers and numerical values).

    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
     거고
    1.16
    but
    1.13
    。
    1.13
     but
    1.11
     mutta
    1.09
     причем
    1.02
     sodass
    1.01
     但
    1.00
    ។
    0.99
    但
    0.98
    POSITIVE LOGITS
     unlike
    1.23
     along
    1.20
     unsurprisingly
    1.10
     unbek
    1.05
     despite
    1.04
     wraz
    1.02
     apesar
    1.02
     like
    0.99
     coupled
    0.98
     however
    0.98
    Activations Density 0.356%

    No Known Activations