© 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. 13647
    Prev
    Next
    INDEX
    Explanations

    October and autumn terms

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

    The neuron strongly activates on “pumpkin” (including pumpkin-spice) and related autumnal cooking terms.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Feb
    1.29
    Feb
    1.20
     봄
    1.06
     April
    1.05
     March
    1.03
    봄
    1.03
     June
    0.99
    feb
    0.99
    春
    0.99
     Jan
    0.98
    POSITIVE LOGITS
    October
    2.33
     October
    2.30
     OCTOBER
    2.19
     окт
    2.14
     अक्टूबर
    2.11
     octobre
    2.09
     Oktober
    2.08
     oktober
    2.08
     Oct
    2.05
     octubre
    2.05
    Activations Density 0.470%

    No Known Activations