© 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. 10-GEMMASCOPE-RES-131K
    7. 112687
    Prev
    Next
    INDEX
    Explanations

    website links and references

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

    URLs or web addresses, particularly those containing "sportsreference.com," "rssf.com," or other reference/database websites.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on mentions of the National Center for Biotechnology Information (NCBI) and its associated database/resource URLs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     to
    -1.34
     not
    -1.33
    '
    -1.16
    んでも
    -1.16
     and
    -1.15
    ͘
    -1.14
    ائی
    -1.12
     sehari
    -1.11
    gede
    -1.09
     or
    -1.07
    POSITIVE LOGITS
    坚定
    1.39
     there
    1.37
     hır
    1.35
    籥
    1.34
    瓛
    1.32
     sorprender
    1.30
    ⎓
    1.30
    は以下の
    1.27
     necesidades
    1.27
    rité
    1.25
    Activations Density 0.020%

    No Known Activations