© 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. 10-GEMMASCOPE-RES-131K
    7. 70146
    Prev
    Next
    INDEX
    Explanations

    user id, document, input

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

    The neuron consistently activates on the token “user,” i.e. it detects mentions of “user” (as in “user id,” “user input,” etc.).

    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
    y
    -3.22
    ’
    -2.97
    m
    -2.97
    and
    -2.77
    s
    -2.69
    x
    -2.67
    k
    -2.61
    n
    -2.50
    絰
    -2.48
    h
    -2.47
    POSITIVE LOGITS
     They
    3.00
     Their
    2.84
    噥
    2.67
     user
    2.39
    ୌ
    2.36
    ſelf
    2.27
    谞
    2.20
    xnn
    2.14
    🢒
    2.14
    geſ
    2.13
    Activations Density 0.032%

    No Known Activations