© 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. 106628
    Prev
    Next
    INDEX
    Explanations

    author tags, versions, urls

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

    The neuron fires on numeric tokens—years, version numbers, counts, and other multi-digit numbers in code or documentation.

    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
    Kep
    -0.79
    न्त
    -0.77
    ஷ
    -0.70
    strö
    -0.70
     discriminate
    -0.69
     coz
    -0.68
     Pure
    -0.67
    Salut
    -0.65
     lại
    -0.65
     Kep
    -0.65
    POSITIVE LOGITS
    igraph
    0.73
     seasoning
    0.73
     RL
    0.72
    itus
    0.68
    brooks
    0.67
    lug
    0.67
     souvenir
    0.67
    ໂ
    0.67
    RL
    0.66
     ^(
    0.66
    Activations Density 0.090%

    No Known Activations