© 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. 22-GEMMASCOPE-RES-131K
    7. 34832
    Prev
    Next
    INDEX
    Explanations

    optimal strategies and choices

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

    The neuron is tuned to detect numerical quantities and parameter values (numbers, digits, and quantitative expressions) in technical 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_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
     botines
    -1.08
    ván
    -1.07
     bolsos
    -1.03
     poliuret
    -1.02
    unik
    -1.02
    -1.00
    crites
    -0.98
    ømme
    -0.98
     extré
    -0.98
     炖
    -0.96
    POSITIVE LOGITS
     for
    1.78
     strategy
    1.33
     choice
    1.30
     optimal
    1.30
     to
    1.28
     best
    1.24
     strategies
    1.23
     choices
    1.22
     decisions
    1.20
     should
    1.15
    Activations Density 0.067%

    No Known Activations