© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67417
    Prev
    Next
    INDEX
    Explanations

    average per day

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

    This neuron is effectively inactive and does not respond to any patterns in the text.

    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
     Ș
    -0.87
    melte
    -0.79
    stā
    -0.79
     so
    -0.77
    равни
    -0.75
    »-
    -0.74
    äsche
    -0.72
    付属
    -0.72
     февраля
    -0.71
    をしていた
    -0.71
    POSITIVE LOGITS
     lebih
    0.94
    Ö
    0.85
     персонал
    0.85
    RDONLY
    0.83
    thodoxy
    0.81
    illon
    0.81
     eventuell
    0.79
    rimidine
    0.78
     Moose
    0.78
     handen
    0.77
    Activations Density 0.016%

    No Known Activations