© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33637
    Prev
    Next
    INDEX
    Explanations

    follow on social media

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

    The neuron detects calls to action prompting the reader to follow or contact the author on social media (e.g. “Follow us on Twitter”).

    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
     miejsce
    -1.00
    第一步
    -0.95
     liitty
    -0.94
    hotra
    -0.91
     eikä
    -0.90
     previous
    -0.90
    øk
    -0.90
    经纪
    -0.88
     предыду
    -0.88
     gemeins
    -0.87
    POSITIVE LOGITS
     on
    4.00
     @
    1.54
     على
    1.40
    บน
    1.38
     (@
    1.25
    //@
    1.19
     trên
    1.19
    :@
    1.17
    @_
    1.15
    |@
    1.15
    Activations Density 0.020%

    No Known Activations