© 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. 3593
    Prev
    Next
    INDEX
    Explanations

    give me

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

    The neuron detects occurrences of the verb “give” (in its various forms such as give, gives, gave, given, giving).

    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
    ながら
    0.80
    te
    0.73
    g
    0.71
    dere
    0.69
    gesteld
    0.68
    ላት
    0.67
     barriers
    0.66
    峪
    0.65
    !}
    0.64
    मिस्ट्री
    0.62
    POSITIVE LOGITS
     rise
    1.12
    予
    1.08
     tặng
    0.93
     birth
    0.82
     generously
    0.81
     impression
    0.81
    impression
    0.79
    Rise
    0.75
     Rise
    0.74
     indication
    0.73
    Activations Density 0.190%

    No Known Activations