© 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. 35134
    Prev
    Next
    INDEX
    Explanations

    orders, datasets, Eyes, deletions, most, cases

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

    The neuron fires strongly on substantive “content” tokens — especially numbers, technical terms, and other domain‐specific nouns and measurements — rather than on common function words.

    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
    tų
    -1.05
     सभी
    -0.99
    enum
    -0.87
    着一个
    -0.87
     is
    -0.82
     main
    -0.81
    자인
    -0.80
    ニ
    -0.80
     reactants
    -0.79
     synchronous
    -0.78
    POSITIVE LOGITS
     cases
    1.33
    mostly
    1.20
    Mostly
    1.09
    noons
    1.08
     jedes
    1.06
     каждого
    1.05
    每一个
    1.02
     either
    0.99
    either
    0.98
    sometimes
    0.98
    Activations Density 0.251%

    No Known Activations