© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 131059
    Prev
    Next
    INDEX
    Explanations

    domain prefixes

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

    The neuron activates strongly on two‐letter country codes (like “au,” “de,” “fr,” “cz,” etc.) in package or import statements.

    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
     because
    -2.56
     being
    -2.44
     or
    -2.39
    ありますが
    -2.25
     any
    -2.17
     undoubtedly
    -2.16
     possibly
    -2.09
     having
    -2.08
     evidently
    -2.06
     unquestionably
    -2.06
    POSITIVE LOGITS
    鼋
    2.31
     uſ
    1.98
    蛲
    1.95
     bénévol
    1.88
     juſt
    1.88
     gela
    1.87
     mélang
    1.84
     they
    1.84
     таких
    1.77
     corriger
    1.77
    Activations Density 0.009%

    No Known Activations