© 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. 9523
    Prev
    Next
    INDEX
    Explanations

    command line and code snippets

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

    The neuron activates on standalone numeric literals (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
    ђе
    -1.16
    AtPosition
    -1.12
    dienne
    -1.06
    \'
    -1.05
    емо
    -1.05
     resultant
    -1.05
     cinturón
    -1.05
    胸口
    -1.04
     znajdziesz
    -1.02
     Commentaires
    -1.01
    POSITIVE LOGITS
    Argumento
    1.20
    llac
    1.16
    inerario
    1.15
    etine
    1.15
    美味しく
    1.09
     entusiasmo
    1.05
    inerary
    1.03
    黯
    1.03
     élar
    1.03
    tività
    1.02
    Activations Density 0.003%

    No Known Activations