© 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. 80722
    Prev
    Next
    INDEX
    Explanations

    in the world and earth

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

    This neuron detects emphatic question phrases that include a wh-word plus a location/intensifier (e.g. “how in the world,” “what on earth,” “why in the name of all things holy”).

    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
     ire
    -1.30
     ベン
    -1.23
     exas
    -1.20
     rile
    -1.16
     yanı
    -1.15
     لأنه
    -1.13
     綺麗
    -1.13
    up
    -1.12
    ємо
    -1.10
     其他
    -1.10
    POSITIVE LOGITS
    standing
    1.52
     textu
    1.40
    mainAxisSize
    1.39
     karier
    1.38
    телем
    1.38
    adamia
    1.38
    geſ
    1.38
     pesar
    1.37
    )$.
    1.36
     historia
    1.36
    Activations Density 0.015%

    No Known Activations