© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90728
    Prev
    Next
    INDEX
    Explanations

    targets and goals

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

    The neuron activates on numeric tokens (years, section numbers, percentages, and other standalone 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_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
     useSelector
    -0.77
     Sommers
    -0.76
    ouard
    -0.75
     noved
    -0.74
     vacunas
    -0.73
     ধ
    -0.71
    ukų
    -0.71
     Zang
    -0.70
     trastornos
    -0.70
     circunstancias
    -0.69
    POSITIVE LOGITS
     targets
    3.03
     target
    2.64
    targets
    2.28
     Targets
    2.23
    Targets
    2.05
    target
    2.03
    Target
    1.90
     Target
    1.77
    目标
    1.76
    目標
    1.70
    Activations Density 0.018%

    No Known Activations