© 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. 22068
    Prev
    Next
    INDEX
    Explanations

    sock and socket related terms

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

    This neuron detects occurrences of the substring “sock” (as in “sock,” “socks,” or identifiers containing “sock”).

    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
    .
    -3.28
    vantaged
    -3.02
     were
    -2.92
    of
    -2.88
     vorigen
    -2.44
    ですが
    -2.44
    $
    -2.42
     которых
    -2.39
    <td>
    -2.38
    ありますが
    -2.38
    POSITIVE LOGITS
    the
    3.23
    {
    2.77
    ᄍ
    2.55
    鴬
    2.44
     padx
    2.44
    鼉
    2.44
     BOTH
    2.42
    迎来
    2.31
    悵
    2.28
    齜
    2.28
    Activations Density 0.002%

    No Known Activations