© 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. 22-GEMMASCOPE-RES-131K
    7. 341
    Prev
    Next
    INDEX
    Explanations

    algebraic expressions and equations

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

    The neuron selectively responds to occurrences of the square‐root notation “sqrt(…)” (and its surrounding numeric/math syntax).

    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
     durant
    -1.16
    ﻷ
    -1.07
    </h1>
    -1.00
     dictionnaire
    -0.97
    ϫ
    -0.95
     durante
    -0.91
     acest
    -0.90
    during
    -0.90
    corer
    -0.90
    quire
    -0.89
    POSITIVE LOGITS
     will
    1.22
    誨
    1.02
     Neither
    1.00
     slightly
    0.99
     two
    0.98
    Both
    0.98
     Both
    0.98
    Sleepy
    0.97
    以上です
    0.96
     TWO
    0.94
    Activations Density 0.011%

    No Known Activations