© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69716
    Prev
    Next
    INDEX
    Explanations

    producer or producers

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

    The neuron detects the word "producer" or "producers" in various contexts, including software, media, manufacturing, and agriculture.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    .''
    -2.59
    umumkan
    -2.58
    ,''
    -2.55
     sickly
    -2.50
     '
    -2.50
    趿
    -2.47
    }
    -2.45
    において
    -2.41
     booming
    -2.41
     nowych
    -2.34
    POSITIVE LOGITS
     We
    2.73
     Betracht
    2.59
    ’，
    2.52
    鹟
    2.50
    рений
    2.36
     تغذ
    2.20
     และ
    2.16
    𖤣
    2.13
    缡
    2.09
    琑
    2.09
    Activations Density 0.011%

    No Known Activations