© 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. 22-GEMMASCOPE-RES-131K
    7. 129592
    Prev
    Next
    INDEX
    Explanations

    The neuron fires selectively on the names of methods in fluent‐API chains (e.g. format, option, select, addData).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    programmer keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    1
    -1.30
    もありますが
    -1.17
     スペシャル
    -1.17
    ⊖
    -1.15
     JAKARTA
    -1.14
     CLEANING
    -1.12
     ENGINEERS
    -1.11
     fré
    -1.10
    を持っている
    -1.09
    😖
    -1.08
    POSITIVE LOGITS
    આ
    1.17
    škas
    1.16
    आई
    1.15
    અ
    1.13
     conformidad
    1.06
     anstatt
    1.05
     různých
    1.04
    –
    1.04
     различных
    1.03
    大丈夫です
    1.02
    Activations Density 0.008%

    No Known Activations