© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13689
    Prev
    Next
    INDEX
    Explanations

    describes, notes

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

    The neuron detects scholarly attribution or reporting cues—words like “describes,” “reports,” “notes,” “reviews,” etc., that signal a citation or reference.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     your
    -1.08
    ustomed
    -1.05
     '/';
    -1.02
     irgende
    -1.01
    }
    
    -1.01
    嚕
    -1.00
     cauza
    -0.99
     />
    
    -0.97
     deinem
    -0.97
    мання
    -0.96
    POSITIVE LOGITS
     in
    1.45
     this
    1.39
     these
    1.31
     for
    1.23
     that
    1.10
     even
    1.06
     how
    1.04
      “
    1.03
     three
    1.02
     cortinas
    1.00
    Activations Density 0.030%

    No Known Activations