© 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. 13749
    Prev
    Next
    INDEX
    Explanations

    respectively / each

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

    The neuron fires on descriptive content words—especially adjectives and adverbs that specify properties (e.g. color, size, direction, nationality).

    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
    Ме
    0.70
    ﻌ
    0.70
     ಇತರ
    0.68
     અન્ય
    0.67
    ﾋ
    0.65
     ಕಾಂಗ್ರೆ
    0.64
     നാല
    0.63
     інші
    0.63
    Со
    0.62
    ବ
    0.62
    POSITIVE LOGITS
     alike
    1.22
     jeweils
    1.06
     respectivamente
    0.90
     respectively
    0.89
     respectivement
    0.88
     serta
    0.81
     sowie
    0.80
     oraz
    0.79
    などの
    0.77
     economies
    0.77
    Activations Density 0.325%

    No Known Activations