© 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. 84345
    Prev
    Next
    INDEX
    Explanations

    queries

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

    The neuron fires strongly on the word “queries” (and its close variants), i.e. mentions of queries.

    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
     với
    -2.94
    \
    -2.91
     WITH
    -2.84
    𓐍
    -2.83
     wth
    -2.81
    t
    -2.70
    ة
    -2.64
     {
    -2.59
    ing
    -2.52
    "—
    -2.44
    POSITIVE LOGITS
    CHREIB
    3.38
    vantaged
    2.81
    </h3>
    2.77
    öpfer
    2.58
    瘓
    2.53
    .
    2.47
    灩
    2.38
    驁
    2.31
    of
    2.27
    ſures
    2.25
    Activations Density 0.006%

    No Known Activations