© 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. 119592
    Prev
    Next
    INDEX
    Explanations

    Notch signaling pathway

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

    Neuron 4 detects programming and scientific notations, particularly double colon operators and hyphenated symbols in code or technical documentation.

    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
    ’
    -1.76
    ("/
    -1.53
    ませて
    -1.48
     According
    -1.45
    ownika
    -1.42
    ,”
    -1.41
     afectar
    -1.41
    Whoever
    -1.31
    Дети
    -1.31
    ,(
    -1.31
    POSITIVE LOGITS
     it
    1.98
     not
    1.63
     necessary
    1.51
     what
    1.48
    mêmes
    1.38
     stolet
    1.34
     there
    1.32
    ﺶ
    1.30
     contributo
    1.30
     accomplish
    1.29
    Activations Density 0.074%

    No Known Activations