© 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. 118916
    Prev
    Next
    INDEX
    Explanations

    chemical and biological processes

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

    programming and technical terms related to scientific and computational processes.

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

    The neuron activates on numeric tokens representing decimal or floating‐point values in the text.

    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
    2
    -3.58
    "
    -2.88
    3
    -2.86
    us
    -2.84
    te
    -2.66
    7
    -2.66
    le
    -2.61
    w
    -2.58
    泚
    -2.50
    1
    -2.48
    POSITIVE LOGITS
     书法
    2.69
    我们要
    2.56
     寫
    2.23
     termed
    2.23
    تال
    2.17
    对了
    2.14
     químicas
    2.14
    我们是
    2.11
    学校の
    2.03
    筚
    2.03
    Activations Density 0.004%

    No Known Activations