© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13559
    Prev
    Next
    INDEX
    Explanations

    code delimiters

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

    The neuron fires on numeric tokens (especially decimal numbers and other number strings).

    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
    -
    -1.69
     gruppe
    -1.61
     guerrero
    -1.50
     peluche
    -1.45
     variedade
    -1.44
     vogel
    -1.43
    МІ
    -1.43
    isés
    -1.41
     komment
    -1.41
     frambo
    -1.39
    POSITIVE LOGITS
    ↵↵
    1.48
    Would
    1.45
    𝙶
    1.38
     to
    1.38
     it
    1.36
    𝙜
    1.32
    Preparazione
    1.31
     に関する
    1.20
    bbons
    1.20
     ursprüng
    1.20
    Activations Density 0.003%

    No Known Activations