© 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. 22-GEMMASCOPE-RES-131K
    4. 12673
    Prev
    Next
    INDEX
    Explanations

    crucial tracks levels confirmed week sequencing

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

    words related to laboratory procedures and experimental methods.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron specializes in spotting quantitative measurements—numerical values, units, and other numeric data reported in scientific contexts.

    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
     you
    -1.70
     your
    -1.63
     APPELLANT
    -1.30
    对你
    -1.29
     kwamba
    -1.28
     desglose
    -1.21
     almendras
    -1.20
     emocionante
    -1.18
     recorte
    -1.17
    Функ
    -1.16
    POSITIVE LOGITS
     was
    1.34
     الشاشة
    1.34
     occasionally
    1.34
     to
    1.34
     روسیه
    1.31
    requently
    1.24
     nostri
    1.19
     siempre
    1.17
     jsem
    1.17
    城市的
    1.16
    Activations Density 0.049%

    No Known Activations