© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 65978
    Prev
    Next
    INDEX
    Explanations

    web scripting and styling

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

    The neuron fires on the slash character “/” in MIME‐type strings (e.g. the “/” in “text/javascript,” “text/css,” etc.).

    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
    
    -1.52
     Spanyol
    -1.48
     tă
    -1.38
    ᜀ
    -1.35
    ೞ
    -1.34
     素描
    -1.32
     做法
    -1.32
     acrí
    -1.31
     estrena
    -1.31
     rús
    -1.30
    POSITIVE LOGITS
    u
    1.53
     fairly
    1.30
     поэтому
    1.30
     urusan
    1.29
     ribuan
    1.27
     aanzien
    1.24
     они
    1.24
    you
    1.22
     kunjungan
    1.22
     moderately
    1.21
    Activations Density 0.004%

    No Known Activations