© 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. 129231
    Prev
    Next
    INDEX
    Explanations

    The neuron detects the period separators in deeply nested dotted package or import paths (i.e. the “.” tokens between components in fully qualified names).

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

    programming 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
    ınıza
    -1.18
     its
    -1.15
     Traducción
    -1.00
     Posteriormente
    -1.00
    hydrogenase
    -0.98
     Allí
    -0.97
    oubtedly
    -0.96
     seus
    -0.96
    颛
    -0.95
    了一遍
    -0.93
    POSITIVE LOGITS
     kuiten
    1.17
     utils
    1.04
     cardiovas
    1.02
     inclus
    1.01
    læ
    0.97
     aboli
    0.96
    utils
    0.95
    wider
    0.95
    0.94
     imobili
    0.93
    Activations Density 0.018%

    No Known Activations