© 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. 127396
    Prev
    Next
    INDEX
    Explanations

    know nothing/much about

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

    The neuron detects phrases expressing the author’s admitted ignorance (e.g. “know nothing about,” “don’t know anything about,” “know little about,” etc.).

    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
     the
    -1.98
    こんばん
    -1.38
    〬
    -1.37
     if
    -1.37
    第一个
    -1.34
     "
    -1.33
     ضعف
    -1.32
    幛
    -1.32
    ୩
    -1.32
     להם
    -1.27
    POSITIVE LOGITS
     of
    1.95
    .
    1.67
     Redewendung
    1.46
    當中
    1.39
     fatte
    1.38
    momile
    1.33
     orari
    1.33
     occhi
    1.30
     folgender
    1.27
    ASTIC
    1.27
    Activations Density 0.015%

    No Known Activations