© 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. 111651
    Prev
    Next
    INDEX
    Explanations

    payable, clickable, Makefile

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

    the word "payable" in financial or legal contexts, and the word "clickable" in technical or programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on words ending in the suffix “-able.”

    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
     —
    -3.20
    ’
    -2.83
    ing
    -2.67
    ﱠ
    -2.67
    疴
    -2.38
     ซึ่ง
    -2.36
    翼翼
    -2.36
     -
    -2.33
     Which
    -2.31
    祭り
    -2.25
    POSITIVE LOGITS
    e
    2.56
    とりあえず
    2.42
    ка
    2.42
     millioner
    2.41
     аккура
    2.28
    蕺
    2.28
    ਲ਼
    2.25
    это
    2.22
    mathrm
    2.20
    )
    2.17
    Activations Density 0.010%

    No Known Activations