© 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. 10-GEMMASCOPE-RES-131K
    7. 86658
    Prev
    Next
    INDEX
    Explanations

    compiler warns or errors

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

    This neuron lights up on the key subject and action words that kick off the explanatory or answer sentences (e.g. “game,” “system,” “compiler,” “body,” “will,” “give,” “you,” etc.).

    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
     such
    -1.20
     می‌توان
    -1.16
    ênes
    -1.15
    ÑOS
    -1.13
    
    -1.13
     sánh
    -1.08
    🦏
    -1.07
     CALIFOR
    -1.07
    gelen
    -1.05
    lican
    -1.05
    POSITIVE LOGITS
     didn
    1.29
     its
    1.13
    IP
    1.09
     itself
    1.09
     not
    1.08
     merry
    1.06
     just
    1.04
     want
    1.04
     as
    1.01
    给予
    1.01
    Activations Density 0.192%

    No Known Activations