© 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. 71718
    Prev
    Next
    INDEX
    Explanations

    plist file and related content

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

    The neuron activates whenever it sees the token “list” (including as part of “plist”).

    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
    When
    -2.02
     ersten
    -1.91
    u
    -1.79
    In
    -1.75
    Sometimes
    -1.70
    is
    -1.63
     longtime
    -1.59
    ar
    -1.55
    Because
    -1.54
     ensures
    -1.52
    POSITIVE LOGITS
     gouttes
    1.74
    ſſen
    1.74
    ご利用
    1.69
    didn
    1.69
    ᯾
    1.65
    ’
    1.63
     vernis
    1.63
    峮
    1.62
    眛
    1.61
     restes
    1.59
    Activations Density 0.001%

    No Known Activations