© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72860
    Prev
    Next
    INDEX
    Explanations

    a host of

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

    The neuron fires on collective‐quantity expressions, i.e. words like “host,” “bevy,” or “slew” when they appear with “of” to mean “a large number of.”

    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
    $
    -1.91
    .
    -1.66
     this
    -1.66
     your
    -1.63
    (
    -1.48
     твои
    -1.46
     garantiert
    -1.46
    شاركة
    -1.45
    年後
    -1.45
     Öffnen
    -1.42
    POSITIVE LOGITS
    );
    1.83
    各样的
    1.74
    InstrumentedTest
    1.70
    /");
    1.66
    ⬣
    1.59
    autoreleasepool
    1.58
    これも
    1.55
     они
    1.54
    ekš
    1.52
    鑪
    1.52
    Activations Density 0.041%

    No Known Activations