© 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-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99590
    Prev
    Next
    INDEX
    Explanations

    percentage of

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

    The neuron activates on numeric percentage mentions (i.e., “percent” with a preceding number).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     
    -1.74
     those
    -1.30
     it
    -1.27
    さてさて
    -1.26
    さぁ
    -1.23
     selbst
    -1.22
    時も
    -1.21
     empfehlen
    -1.20
    そろそろ
    -1.19
     ...
    -1.16
    POSITIVE LOGITS
    原始内容存档于
    1.65
    raujo
    1.54
     flotte
    1.54
     getItemCount
    1.48
     ferie
    1.44
    تیجه
    1.43
    lında
    1.41
     grà
    1.41
     vuitton
    1.36
     crede
    1.34
    Activations Density 0.010%

    No Known Activations