© 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. 85482
    Prev
    Next
    INDEX
    Explanations

    programming configuration and structure

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

    The neuron fires on mentions of software frameworks, libraries, and related technical components.

    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
    -
    -2.33
     nine
    -2.19
     not
    -2.16
     less
    -2.13
     after
    -2.11
    After
    -2.05
    after
    -2.05
    ??
    -2.03
     eight
    -2.03
    :
    -2.02
    POSITIVE LOGITS
     teolog
    2.36
     ſen
    2.30
     professione
    2.16
     vetores
    2.14
     illustratie
    2.14
     maksi
    2.13
    rolex
    2.13
     ſal
    2.08
     fré
    2.05
     Eſ
    2.05
    Activations Density 2.312%

    No Known Activations