© 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. 111688
    Prev
    Next
    INDEX
    Explanations

    delightful things or cystic fibrosis

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

    The neuron activates for the word "delightful" and its variants.

    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
    {
    -3.08
    可以
    -2.30
    t
    -2.20
    有可能
    -2.09
     intrepid
    -2.08
     The
    -2.08
    _));
    -2.05
    ?
    -2.05
    lorin
    -1.98
    5
    -1.96
    POSITIVE LOGITS
    ,’
    2.77
     (‘
    2.38
    咈
    2.28
    ጮ
    2.27
    ’:
    2.25
     tais
    2.20
    τής
    2.16
     analisis
    2.09
    媗
    2.08
    CHELL
    2.06
    Activations Density 0.003%

    No Known Activations