© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33095
    Prev
    Next
    INDEX
    Explanations

    både and and

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

    The neuron fires on numeric tokens, especially multi-digit numbers.

    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
     nestled
    -0.98
    …..
    -0.94
     provide
    -0.94
     your
    -0.93
    ….
    -0.93
    Citiți
    -0.93
    mrow
    -0.91
     for
    -0.91
    Tazama
    -0.90
     getting
    -0.85
    POSITIVE LOGITS
     både
    1.61
     zowel
    1.54
    both
    1.39
    Both
    1.17
     both
    1.14
     दोनों
    1.10
    BOTH
    1.09
     zarówno
    1.07
     sowohl
    1.05
     BOTH
    1.02
    Activations Density 0.017%

    No Known Activations