© 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. 34-GEMMASCOPE-RES-131K
    7. 57816
    Prev
    Next
    INDEX
    Explanations

    numbers and versioning

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

    The neuron detects technical identifiers made up of numbers (often mixed with letters or punctuation), such as version numbers, classification codes, and other numeric codes.

    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
     какво
    -0.84
     They
    -0.80
     փ
    -0.79
     màn
    -0.78
     Vertrauen
    -0.77
     ihnen
    -0.75
    deles
    -0.74
    They
    -0.73
     little
    -0.72
     Environmental
    -0.71
    POSITIVE LOGITS
     quim
    0.80
    ilish
    0.77
     BRIEF
    0.77
    𓐍
    0.76
    вање
    0.76
    鏗
    0.76
    inerario
    0.76
    Ꮫ
    0.75
    allero
    0.75
     naszych
    0.75
    Activations Density 0.019%

    No Known Activations