© 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. 65828
    Prev
    Next
    INDEX
    Explanations

    code definitions and attributes

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

    The neuron activates on programming‐language identifiers—chiefly variable and parameter names.

    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
     while
    -1.17
     anuncio
    -1.08
     Congrès
    -1.05
     Krzysz
    -1.04
     komplette
    -1.03
    although
    -1.00
     vaksin
    -1.00
     kül
    -0.98
     in
    -0.95
    Besos
    -0.94
    POSITIVE LOGITS
    。“
    1.41
    edom
    1.23
    addContainer
    1.20
     contactez
    1.20
    PRNewswire
    1.18
     그리고
    1.16
    tomans
    1.13
    ):}
    1.13
     señales
    1.11
     jonka
    1.11
    Activations Density 0.058%

    No Known Activations