© 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. 71065
    Prev
    Next
    INDEX
    Explanations

    Appellee, appellant, court, Texas

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

    The neuron fires on long runs of whitespace (large spans of spaces or indentation).

    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
     refused
    -1.29
     those
    -1.28
     because
    -1.27
     what
    -1.27
     seemed
    -1.22
     people
    -1.21
     asked
    -1.16
     contesta
    -1.16
     rapports
    -1.13
     just
    -1.13
    POSITIVE LOGITS
     alcune
    1.22
     alguns
    1.16
     miesto
    1.16
     ผู้
    1.16
     Dinas
    1.14
     insanely
    1.14
     (!__
    1.11
    oxidants
    1.11
     wciąż
    1.09
     magnificent
    1.07
    Activations Density 0.006%

    No Known Activations