© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13150
    Prev
    Next
    INDEX
    Explanations

    percentage of

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

    The neuron is triggered by the word “percentage” (especially in “percentage of …”) marking percentage‐of expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ৢ
    -2.48
    i
    -2.25
     Now
    -2.17
     But
    -2.11
     charisma
    -2.06
     unglaub
    -1.97
     senseless
    -1.96
     marathon
    -1.95
    亮相
    -1.95
    但在
    -1.93
    POSITIVE LOGITS
    んですが
    2.72
     of
    2.58
     <",
    2.52
     vaksin
    2.31
    趼
    2.23
    靫
    2.14
    んですけど
    2.08
    嘤
    2.06
     >",
    2.06
     menyen
    2.06
    Activations Density 0.007%

    No Known Activations