© 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. 84141
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

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

    The neuron activates on numeric tokens (numbers, including integers and decimals).

    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
     also
    -1.30
    همچنین
    -1.23
    ↵↵
    -1.19
     также
    -1.14
     می‌ده
    -1.08
    licitations
    -1.06
    0
    -1.02
    Также
    -1.00
     and
    -0.99
    enie
    -0.99
    POSITIVE LOGITS
    ഉ
    1.23
    ಆ
    1.14
    ಅ
    1.13
     Их
    1.13
    味的
    1.09
     Justiça
    1.08
     Popis
    1.00
    Cuál
    0.99
     Their
    0.97
     kurie
    0.97
    Activations Density 0.159%

    No Known Activations