© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8085
    Prev
    Next
    INDEX
    Explanations

    java list structures

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

    This neuron responds to mentions of “list” (including the List type or the word “list”).

    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
    uropa
    -1.44
    ynthetic
    -1.43
    $
    -1.41
    ibilidade
    -1.41
    netics
    -1.39
    ENT
    -1.36
     wob
    -1.34
    是一个
    -1.30
     CON
    -1.30
    ynthesis
    -1.29
    POSITIVE LOGITS
     are
    1.48
    guigu
    1.45
     these
    1.43
    shein
    1.37
    yyj
    1.36
     the
    1.36
     it
    1.30
    rolex
    1.28
    djang
    1.24
    @@@@@
    1.23
    Activations Density 0.037%

    No Known Activations