© 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. 39075
    Prev
    Next
    INDEX
    Explanations

    fancy dress or list of

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

    The neuron is triggered by emoji or similar special Unicode pictorial characters.

    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
     ”
    -2.39
    ”;
    -2.17
     eer
    -2.02
     supposed
    -1.96
    ”-
    -1.95
    </i>
    -1.89
     ''
    -1.88
     formada
    -1.80
     desmotiv
    -1.78
     ‘‘
    -1.77
    POSITIVE LOGITS
    ૩
    2.11
    to
    2.11
    klart
    2.09
    鯪
    1.97
    Some
    1.97
    There
    1.90
    ۴
    1.89
    tiest
    1.85
    gifter
    1.85
    This
    1.84
    Activations Density 0.000%

    No Known Activations