© 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. 22-GEMMASCOPE-RES-131K
    7. 26825
    Prev
    Next
    INDEX
    Explanations

    various programming languages and libraries

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

    The neuron fires on “Q”-prefixed identifiers (especially C++/Qt class names and include paths).

    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
     lentes
    -1.37
     木製
    -1.33
     aranha
    -1.27
     generó
    -1.25
    หรือ
    -1.23
    𖧵
    -1.23
     ако
    -1.22
     یا
    -1.20
     tém
    -1.20
     kabát
    -1.20
    POSITIVE LOGITS
    AFFIRMED
    1.10
    H
    1.07
    something
    1.07
    M
    1.04
     something
    1.03
     everything
    1.02
    a
    1.02
    O
    1.02
     what
    1.01
     mouseY
    1.01
    Activations Density 0.013%

    No Known Activations