© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11760
    Prev
    Next
    INDEX
    Explanations

    comics

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

    comma separated lists, "Com" variants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rů
    0.45
    ASON
    0.39
     Foot
    0.39
     จริง
    0.38
     Rest
    0.38
     ք
    0.38
    idiu
    0.38
     athlet
    0.38
     cle
    0.37
    झा
    0.37
    POSITIVE LOGITS
    Com
    0.66
     Com
    0.65
     комі
    0.61
     Comet
    0.58
     COMM
    0.57
    彗
    0.56
    COM
    0.55
     Comm
    0.54
    Comm
    0.53
     COM
    0.52
    Activations Density 0.143%

    No Known Activations