© 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. 90461
    Prev
    Next
    INDEX
    Explanations

    team contexts

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

    This neuron detects occurrences of the word “team” (especially in identifiers like team_id or class names) in code or structured data.

    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
     but
    -2.86
     Of
    -2.31
     We
    -2.25
    ."
    -2.20
     along
    -2.05
     no
    -1.99
    ")
    -1.95
     as
    -1.95
    と言
    -1.90
    ги
    -1.88
    POSITIVE LOGITS
     seksi
    2.42
    Because
    2.41
     rajut
    2.33
    卝
    2.25
    These
    2.20
     gantung
    2.19
     artistico
    2.16
    Ꮉ
    2.11
     laku
    2.11
     اشار
    2.11
    Activations Density 0.004%

    No Known Activations