© 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. 13969
    Prev
    Next
    INDEX
    Explanations

    wet, dry, cook

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

    The neuron detects numeric quantities and measurement terms (e.g. doses, units, and amounts) in instructional or recipe‐style text.

    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
     વિશ્વ
    0.70
     desafío
    0.66
     obsess
    0.64
     നേടിയ
    0.64
    積極
    0.63
     крупней
    0.63
     במהלך
    0.63
    ！
    0.63
    நாடு
    0.63
     ベビー
    0.62
    POSITIVE LOGITS
     nutritive
    0.74
     smoot
    0.70
     yellowish
    0.69
     geometrical
    0.69
     whitish
    0.69
    颜色
    0.68
     शोभा
    0.68
     साइज
    0.66
     warna
    0.64
     कलर
    0.64
    Activations Density 0.257%

    No Known Activations