© 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. 40004
    Prev
    Next
    INDEX
    Explanations

    ad, cameras, cartridges

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

    The neuron fires strongly on the first “content” word of a new block or heading—i.e. it marks tokens that kick off a fresh paragraph/section.

    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
     rédu
    -1.13
     snar
    -1.05
     zimní
    -1.05
     origini
    -1.00
     zemi
    -1.00
     maravilloso
    -0.99
     forestal
    -0.99
    wouldn
    -0.98
     Situs
    -0.96
    小伙伴
    -0.96
    POSITIVE LOGITS
     and
    1.17
     when
    1.09
     while
    1.03
     with
    0.98
     =
    0.98
    ;
    
    0.96
     &
    0.95
     as
    0.94
     clothing
    0.93
     demostrar
    0.93
    Activations Density 0.093%

    No Known Activations