© 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. 22-GEMMASCOPE-RES-131K
    7. 54081
    Prev
    Next
    INDEX
    Explanations

    fellow people or groups

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

    This neuron detects occurrences of the word “fellow” (when used to address or describe members of a group).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ஂ
    -2.58
     nedenle
    -2.48
     \
    -2.38
    齧
    -2.28
     jiné
    -2.19
     gesamte
    -2.17
    鲀
    -2.17
     oasis
    -2.17
     několika
    -2.17
     másik
    -2.16
    POSITIVE LOGITS
     countryman
    2.41
    而又
    2.28
     namun
    2.27
     minggu
    2.23
    但
    2.20
    leggio
    2.19
    圌
    2.19
    стами
    2.19
     lelaki
    2.17
    鮓
    2.17
    Activations Density 0.006%

    No Known Activations