© 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. 38983
    Prev
    Next
    INDEX
    Explanations

    leaving or completion

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

    The neuron specifically detects occurrences of the JavaScript “toJSON()” method call.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Dacă
    -1.05
     acercarse
    -1.01
    Vezi
    -0.98
    Pentru
    -0.98
    ürt
    -0.97
    indere
    -0.96
     asegurarse
    -0.92
     introducir
    -0.92
    šanās
    -0.92
     acercar
    -0.91
    POSITIVE LOGITS
     leaving
    1.17
     leave
    1.13
     final
    1.12
    leaving
    1.09
    其他的
    1.08
     completed
    1.03
    LEAVE
    1.01
    leaved
    0.99
     outro
    0.97
    すすめ
    0.96
    Activations Density 0.000%

    No Known Activations