© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73334
    Prev
    Next
    INDEX
    Explanations

    other/others in various languages

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

    The neuron fires on hype‐style descriptors in sports write‐ups—words like “shining,” “fellow,” “phen(om),” and player first names (e.g. Andrew) used to build athletic hype.

    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
     or
    -1.23
     could
    -1.11
     which
    -1.11
     can
    -1.10
     would
    -1.05
     rudimentary
    -1.05
     after
    -1.01
     Every
    -1.00
     When
    -1.00
     Additional
    -1.00
    POSITIVE LOGITS
     others
    2.56
     other
    2.50
    others
    2.02
     innych
    1.88
    อื่น
    1.86
     других
    1.82
     anderen
    1.73
     інших
    1.69
     другие
    1.63
     diğer
    1.62
    Activations Density 0.043%

    No Known Activations