© 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. 40094
    Prev
    Next
    INDEX
    Explanations

    email addresses and sender info

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

    The neuron primarily responds to digit‐only tokens (multi‐digit numbers) appearing 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
    がありますが
    -1.38
    ‏‏
    -1.28
     början
    -1.28
     bidra
    -1.26
     Tatsache
    -1.26
     Factbook
    -1.25
    <bos>
    -1.23
     annons
    -1.21
     oferece
    -1.20
     cuisson
    -1.19
    POSITIVE LOGITS
     lessening
    1.50
     salvajes
    1.44
    就不是
    1.40
    忿
    1.38
     зараз
    1.36
    心底
    1.35
     начинают
    1.35
     Pokud
    1.35
    citroen
    1.34
    少なく
    1.32
    Activations Density 0.011%

    No Known Activations