© 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. 22-GEMMASCOPE-RES-131K
    7. 66674
    Prev
    Next
    INDEX
    Explanations

    setting properties

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

    This neuron detects programming code snippets (tokens typical of code syntax rather than natural language).

    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
     evtl
    -1.16
     byen
    -1.16
    brtc
    -1.13
    laria
    -1.12
     erzeugt
    -1.10
    苤
    -1.10
     luscious
    -1.09
     rempli
    -1.08
    是自己
    -1.08
    跸
    -1.07
    POSITIVE LOGITS
     so
    1.20
     in
    1.16
                 
    1.12
     use
    1.12
     made
    1.09
     an
    1.08
     became
    1.07
     also
    1.06
         
    1.03
     one
    1.02
    Activations Density 0.029%

    No Known Activations