© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113959
    Prev
    Next
    INDEX
    Explanations

    stocks, connectionString, feedstock

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

    The neuron fires on occurrences of the noun “stock” or “stocks” (especially in the compound term “feedstock(s)”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    that
    -2.80
    </i>
    -2.38
     که
    -2.31
    旆
    -2.28
    抱歉
    -2.22
    This
    -2.17
    ться
    -2.14
     verschiedener
    -2.09
    These
    -2.08
    𐑂
    -2.06
    POSITIVE LOGITS
    圌
    2.38
    
    2.20
     intend
    2.14
    
    2.03
    볶
    2.02
     キャプ
    2.02
     are
    1.97
     contraseña
    1.95
     også
    1.95
     auch
    1.95
    Activations Density 0.000%

    No Known Activations