© 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. 22205
    Prev
    Next
    INDEX
    Explanations

    ± signs with numbers

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

    The neuron strongly activates on numeric tokens—especially decimal numbers (measurements or statistical values).

    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
    end
    -2.75
    by
    -2.52
    ll
    -2.50
    that
    -2.42
    when
    -2.27
    just
    -2.23
    item
    -2.20
    ti
    -2.17
    section
    -2.14
    How
    -2.13
    POSITIVE LOGITS
     キーホルダー
    2.03
    Epidemiology
    2.02
    grats
    2.02
    ︲
    1.98
    concep
    1.96
    smh
    1.95
    𐐀
    1.80
    Stamina
    1.80
    Diseases
    1.79
    screenshots
    1.76
    Activations Density 0.035%

    No Known Activations