© 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. 111600
    Prev
    Next
    INDEX
    Explanations

    life expectancy, actuarial table, differentials

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

    terminology related to statistical and actuarial analysis, particularly related to mortality rates, life tables, and demographic data.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects occurrences of the word stem “actuar­” in terms like “actuary,” “actuaries,” and “actuarial.”

    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
    pakking
    -1.19
     entrambi
    -1.19
    ('.')
    -1.16
    Tutorials
    -1.13
     aggiungere
    -1.13
    OLOGIA
    -1.11
    䉴
    -1.11
     uner
    -1.11
    
    -1.09
    Realtime
    -1.08
    POSITIVE LOGITS
    Also
    1.38
     like
    1.38
    At
    1.34
    As
    1.29
     Also
    1.27
     these
    1.26
     Botschaft
    1.20
     through
    1.16
    In
    1.16
    These
    1.16
    Activations Density 0.069%

    No Known Activations