© 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. 34-GEMMASCOPE-RES-131K
    7. 93300
    Prev
    Next
    INDEX
    Explanations

    comment section and below

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

    The neuron detects calls to action prompting the reader to leave or share comments (e.g. “comment,” “comments,” “section,” “below”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    josé
    -0.97
     mépris
    -0.94
    Above
    -0.92
     todella
    -0.88
    ţiei
    -0.86
     wichtiger
    -0.83
    くま
    -0.82
     Visser
    -0.82
     in
    -0.81
     unange
    -0.81
    POSITIVE LOGITS
     or
    1.31
     section
    1.27
    !
    1.05
     down
    0.97
     how
    0.94
    gucigalpa
    0.93
     if
    0.91
     space
    0.90
     area
    0.89
    section
    0.88
    Activations Density 0.011%

    No Known Activations