© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7466
    Prev
    Next
    INDEX
    Explanations

    computer science department

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

    The neuron responds to mentions of the field of computer science (e.g. “computer,” “science,” “computer science”).

    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
     明治
    -1.18
     cannabis
    -1.15
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.14
    ابت
    -1.13
    我們
    -1.12
    ↵↵↵↵↵↵↵↵↵↵↵
    -1.11
                                  
    -1.10
    ZT
    -1.10
    各
    -1.09
     whiskey
    -1.08
    POSITIVE LOGITS
     laajenta
    1.41
     municipales
    1.37
    Иск
    1.30
    theres
    1.29
    这句话
    1.26
     seraient
    1.25
     Theres
    1.24
    噱
    1.23
     filós
    1.23
     It
    1.23
    Activations Density 0.181%

    No Known Activations