© 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. 86224
    Prev
    Next
    INDEX
    Explanations

    /* comments and code snippets

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

    This neuron detects JSON-style structural markers—especially the colons and brackets that denote key/value pairs and arrays.

    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
     if
    -1.74
     it
    -1.52
     also
    -1.44
    _
    -1.42
    ,”
    -1.40
    ’
    -1.40
     was
    -1.38
     you
    -1.35
     we
    -1.32
     If
    -1.30
    POSITIVE LOGITS
     jejich
    1.82
    bezpiecz
    1.56
     pourront
    1.50
     Mereka
    1.48
     nové
    1.48
    osob
    1.47
    🛇
    1.46
    璈
    1.46
    ཫ
    1.45
     ممکن
    1.42
    Activations Density 0.000%

    No Known Activations