© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129407
    Prev
    Next
    INDEX
    Explanations

    Amazon affiliate advertising

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

    The neuron fires on long, standalone alphanumeric tokens dominated by digits (e.g. long numeric or hex‐style strings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     diarios
    -1.64
     ancianos
    -1.52
    可在
    -1.49
    ère
    -1.49
    nitř
    -1.49
    şem
    -1.49
    电机
    -1.49
     kterou
    -1.48
     preescolar
    -1.48
     secundaria
    -1.46
    POSITIVE LOGITS
    剮
    1.79
    n
    1.71
    .
    1.64
     För
    1.55
     emporter
    1.50
    臜
    1.50
    m
    1.49
     itinéraire
    1.48
    r
    1.48
    せい
    1.45
    Activations Density 0.004%

    No Known Activations