© 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. 22-GEMMASCOPE-RES-131K
    4. 12711
    Prev
    Next
    INDEX
    Explanations

    percentages or amounts

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

    The neuron fires on numeric tokens (e.g. integers, decimals, percentages) indicating it detects numbers or statistical values in the text.

    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
    丨
    -1.10
     چربی
    -1.09
    albeit
    -1.06
     dianteiro
    -1.05
    ->$
    -1.04
     нашем
    -1.02
    ?????
    -1.02
     åren
    -1.01
     unseren
    -1.00
    ??????
    -1.00
    POSITIVE LOGITS
     overall
    1.23
    וּ
    1.19
     mám
    1.15
     hvě
    1.13
     changes
    1.13
     or
    1.11
     Ruß
    1.08
     last
    1.02
     better
    1.02
     EconPapers
    1.00
    Activations Density 0.033%

    No Known Activations