© 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. 4951
    Prev
    Next
    INDEX
    Explanations

    meaning of words and phrases

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

    The neuron fires on occurrences of the verb “mean” (in its various inflected forms like mean, means, meant) used to express that something signifies or conveys a value.

    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
     Ос
    0.69
    ECH
    0.67
    的做法
    0.66
    ties
    0.65
    c
    0.65
    knot
    0.65
    ETER
    0.64
     이라고
    0.64
    kker
    0.64
    とする
    0.63
    POSITIVE LOGITS
    슨
    0.82
     freedom
    0.72
    你应该
    0.71
     livelihood
    0.71
     reversion
    0.70
     niente
    0.70
     mniej
    0.68
    лід
    0.68
    你可以
    0.64
     sleepless
    0.64
    Activations Density 0.080%

    No Known Activations