© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12602
    Prev
    Next
    INDEX
    Explanations

    garlic butter combination

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

    This neuron activates strongly on decimal numbers (floating‐point numeric tokens) in the text.

    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
    お待ち
    0.68
    e
    0.68
    К
    0.68
    浦
    0.65
    nému
    0.65
     লা
    0.64
    K
    0.64
    ැල
    0.64
    glTranslatef
    0.62
    Mau
    0.62
    POSITIVE LOGITS
     Speaks
    0.87
     Foods
    0.77
     Shit
    0.71
    ㅋㅋ
    0.71
     popolare
    0.70
    નની
    0.70
    㠃
    0.70
     Advertising
    0.69
     alegre
    0.69
     Workplace
    0.69
    Activations Density 0.000%

    No Known Activations