© 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. 22-GEMMASCOPE-RES-131K
    7. 33901
    Prev
    Next
    INDEX
    Explanations

    annual incidence or rate

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

    The neuron flags quantitative data tokens—numbers and related time‐or‐measure words (e.g. “annual,” “monthly,” “daily,” percentages, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Río
    -1.29
    Otro
    -1.14
    Algunas
    -1.09
     тату
    -1.08
    ის
    -1.05
    堪能
    -1.05
    いますが
    -1.02
    ');
    -1.02
    巳
    -1.02
    ksesta
    -0.97
    POSITIVE LOGITS
    客厅
    1.15
     glaubt
    1.11
     worldwide
    1.07
     bleus
    1.07
     implementing
    1.05
     entschieden
    1.05
     nationwide
    1.05
     estimated
    1.05
    total
    1.04
     recurring
    1.03
    Activations Density 0.018%

    No Known Activations