© 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. 5615
    Prev
    Next
    INDEX
    Explanations

    maximum value or number

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

    The neuron fires strongly on occurrences of the token “Max” (e.g. in product/brand names like Maxell or headings labeled “Max”).

    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
    ucceeded
    0.64
    mrow
    0.61
    訳
    0.55
    जीव
    0.55
    implicitly
    0.55
    Truman
    0.55
    नव
    0.54
    શ
    0.54
     defe
    0.54
    Aware
    0.54
    POSITIVE LOGITS
     MAX
    1.09
    िमम
    1.02
     max
    1.00
     maxim
    0.94
     Max
    0.93
     allowable
    0.92
     Maximal
    0.89
     Maxim
    0.89
    MAX
    0.87
    IMUM
    0.84
    Activations Density 0.116%

    No Known Activations