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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 10754
    Prev
    Next
    INDEX
    Explanations

    multi-

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

    The neuron activates on occurrences of the “mult” (especially “multi”) prefix at the start of words.

    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
    雙
    0.80
     двой
    0.75
    Double
    0.71
     双
    0.71
    的双
    0.70
    双
    0.70
     double
    0.70
     Double
    0.68
    double
    0.66
    opian
    0.65
    POSITIVE LOGITS
     multig
    1.20
     mult
    1.16
     multi
    1.13
     Mult
    1.13
     multil
    1.10
     Multi
    1.09
    MULT
    1.09
     multist
    1.09
     MULT
    1.06
    多
    1.05
    Activations Density 0.082%

    No Known Activations