© 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. 44503
    Prev
    Next
    INDEX
    Explanations

    user defined construction

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

    The neuron selectively fires on occurrences of the phrase “user-defined” (especially with its hyphenated form).

    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
     boun
    -1.48
     konkrete
    -1.38
    颢
    -1.37
    lusconi
    -1.34
     mijn
    -1.31
    ladin
    -1.27
    我们可以
    -1.27
     they
    -1.27
    RUnlock
    -1.27
     ее
    -1.26
    POSITIVE LOGITS
    "
    1.76
    <i>
    1.75
    ............
    1.61
    ...............
    1.55
     betreft
    1.54
     about
    1.53
     (−
    1.52
    .{
    1.52
    一般的
    1.51
    <b>
    1.49
    Activations Density 0.019%

    No Known Activations