© 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. 13722
    Prev
    Next
    INDEX
    Explanations

    names following by, and, to, actor

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

    The neuron activates strongly on numeric tokens (multi‐digit numbers and counts).

    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
     prét
    -1.20
    Istorija
    -1.14
    hould
    -1.14
     dekoratif
    -1.13
    viembre
    -1.12
    ㈬
    -1.12
    蟳
    -1.11
    쐈
    -1.09
    
    -1.09
     yaptığı
    -1.09
    POSITIVE LOGITS
     entire
    1.47
     again
    1.44
     mainly
    1.43
     everyone
    1.43
     both
    1.41
     mostly
    1.38
     primarily
    1.32
     basically
    1.27
     reliable
    1.27
     generally
    1.26
    Activations Density 0.010%

    No Known Activations