© 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. 38670
    Prev
    Next
    INDEX
    Explanations

    start of specific names

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

    The neuron detects documentation‐style annotation tokens in code comments (e.g. docblock tags and type‐declaration markers).

    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
     it
    -1.52
    Története
    -1.20
     stabilité
    -1.13
    camiseta
    -1.11
    پاسخ
    -1.10
     ölüm
    -1.08
    หรือ
    -1.05
     Senado
    -1.05
    艫
    -1.04
    pherds
    -1.03
    POSITIVE LOGITS
    1.20
     namens
    1.09
     トイレ
    1.05
    ’
    0.99
    的是
    0.96
     zun
    0.96
     tía
    0.95
    '
    0.95
     aufs
    0.94
    食感
    0.94
    Activations Density 0.000%

    No Known Activations