© 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. 63991
    Prev
    Next
    INDEX
    Explanations

    social media links and mentions

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

    This neuron detects social‐media-style markup elements such as URLs, @-handles, hashtags, ellipses, and other nonword tokens.

    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
     covid
    -1.34
     Covid
    -1.30
    covid
    -1.23
    Covid
    -1.18
    pandemic
    -1.12
     pandemic
    -1.09
     COVID
    -1.09
     noen
    -0.94
     TikTok
    -0.94
    COVID
    -0.91
    POSITIVE LOGITS
     #
    2.03
     @
    1.81
    @
    1.50
    +#
    1.45
     \#
    1.41
     "@
    1.38
     tweeted
    1.36
     ‏
    1.29
     RT
    1.29
    RT
    1.29
    Activations Density 0.028%

    No Known Activations