© 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. 10-GEMMASCOPE-RES-131K
    7. 128740
    Prev
    Next
    INDEX
    Explanations

    starting young activities

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

    The neuron is picking out numeric or quantitative tokens—things like ages, dates, measures, or other number-based information.

    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
     it
    -1.55
     they
    -1.55
     you
    -1.55
     us
    -1.22
     this
    -1.21
    なのです
    -1.20
     is
    -1.20
    another
    -1.19
     inalámbrica
    -1.18
    沙发
    -1.17
    POSITIVE LOGITS
    诶
    1.27
    ᐈ
    1.27
    ਢ
    1.26
    ể
    1.24
     mnoho
    1.21
    IPPI
    1.20
    積極的に
    1.20
    świad
    1.19
     INFORMACIÓN
    1.16
     countless
    1.16
    Activations Density 0.313%

    No Known Activations