© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64770
    Prev
    Next
    INDEX
    Explanations

    method calls and programming operations

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

    This neuron flags tokens that are function or method call names (including chained/dotted calls).

    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
     to
    -1.20
     dè
    -0.99
    はず
    -0.98
     garan
    -0.96
    irii
    -0.93
     ☺️
    -0.89
    iM
    -0.89
    qiang
    -0.88
     promove
    -0.88
    って感じ
    -0.88
    POSITIVE LOGITS
     relatively
    1.13
     although
    1.08
    𝗡
    1.05
     eléctricas
    1.01
    although
    1.01
     cromado
    1.01
    gruß
    0.99
     bolsillos
    0.98
    Selain
    0.98
     alebo
    0.95
    Activations Density 0.009%

    No Known Activations