© 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. 34-GEMMASCOPE-RES-131K
    4. 103120
    Prev
    Next
    INDEX
    Explanations

    additionally, related, scope

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

    This neuron is activated by numeric tokens, i.e. individual digits or numbers 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_34/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
     luft
    -0.82
     SIGNAL
    -0.81
    boks
    -0.79
     francès
    -0.79
     tı
    -0.79
    アーティスト
    -0.79
    ignal
    -0.78
    )"),
    -0.77
     serwis
    -0.76
    nements
    -0.76
    POSITIVE LOGITS
    Therefore
    0.97
     therefore
    0.82
    これ
    0.82
     голова
    0.80
     daarom
    0.79
    ভা
    0.79
    Additionally
    0.76
     außerdem
    0.75
     Therefore
    0.75
     mead
    0.75
    Activations Density 0.011%

    No Known Activations