© 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. 34-GEMMASCOPE-RES-131K
    4. 90978
    Prev
    Next
    INDEX
    Explanations

    country name reports

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

    This neuron detects list‐introduction phrases—words like “reports,” “from,” “the,” and “following” that signal an upcoming enumeration.

    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
     from
    -1.44
     just
    -1.37
     before
    -1.30
     with
    -1.30
     any
    -1.27
     October
    -1.26
     taking
    -1.26
     so
    -1.20
     when
    -1.20
     give
    -1.19
    POSITIVE LOGITS
     betreffende
    1.27
     étudier
    1.17
    
    1.09
     horrid
    1.06
     ADDITIONAL
    1.05
     verborgen
    1.05
     Dinas
    1.04
    possibly
    1.04
     ludicrous
    1.03
     améliorer
    1.02
    Activations Density 0.003%

    No Known Activations