© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 3667
    Prev
    Next
    INDEX
    Explanations

    militant groups and conflict

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

    The neuron strongly activates on occurrences of “militant” (and its plural/derivative forms), identifying mentions of militant actors or groups.

    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
    同上
    -2.61
    真的很
    -2.34
     oldukça
    -2.33
     Grundstück
    -2.33
    大半
    -2.31
     duże
    -2.28
    ımıza
    -2.25
     gerçekten
    -2.22
     člov
    -2.20
     come
    -2.14
    POSITIVE LOGITS
    𓋼
    3.13
     内衣
    2.98
    the
    2.84
    淠
    2.59
    得
    2.58
    鸸
    2.58
    鸱
    2.56
    婓
    2.52
    mathrm
    2.48
     signifikan
    2.44
    Activations Density 0.002%

    No Known Activations