© 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. 37772
    Prev
    Next
    INDEX
    Explanations

    health utility and preferences

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

    concepts related to economic utility and value measurement.

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

    This neuron selectively activates on numeric tokens (multi‐digit numbers) in the text.

    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
     roda
    -0.76
    owed
    -0.76
    statistics
    -0.75
     Héctor
    -0.75
    asjonen
    -0.75
     limites
    -0.74
     PROGRESS
    -0.74
     全国
    -0.72
    Ŕ
    -0.71
    ('../../
    -0.71
    POSITIVE LOGITS
     utility
    3.38
     Utility
    2.63
    utility
    2.59
    Utility
    2.33
     utilities
    2.25
     preferences
    2.16
     Utilities
    1.78
     utils
    1.71
     utilidad
    1.70
     preference
    1.61
    Activations Density 0.035%

    No Known Activations