© 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. 14735
    Prev
    Next
    INDEX
    Explanations

    numbers and citations

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

    The neuron is effectively inactive—it does not respond to any tokens.

    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
     Akti
    -0.87
    适当
    -0.84
    ੭
    -0.84
     similar
    -0.82
    叻
    -0.82
     mengangkat
    -0.82
     balans
    -0.81
     "..\..\..\
    -0.81
     both
    -0.80
     soos
    -0.79
    POSITIVE LOGITS
     Atoms
    0.86
    strijden
    0.83
     quark
    0.82
     IMM
    0.80
     Ikea
    0.78
     phot
    0.78
     grantee
    0.78
    มากกว่า
    0.76
     Adolf
    0.76
     nuc
    0.75
    Activations Density 0.002%

    No Known Activations