© 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-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136185
    Prev
    Next
    INDEX
    Explanations

    This neuron activates with the token "n" often followed by punctuation or specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {}\
    0.43
    ...\
    0.39
    بة
    0.38
    *\
    0.38
     {}\
    0.38
    телями
    0.38
    <\/
    0.38
    .*\
    0.37
    wać
    0.37
    ുകളുടെ
    0.37
    POSITIVE LOGITS
    ಾಯಿತು
    0.39
     kaz
    0.37
     nhiêu
    0.36
     Kaz
    0.36
     systemat
    0.35
     proceed
    0.35
     marie
    0.34
     প্রেসক্লা
    0.34
     solutes
    0.33
     disant
    0.33
    Activations Density 0.001%

    No Known Activations