© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27292
    Prev
    Next
    INDEX
    Explanations

    medical conditions, scientific terms, or code snippets

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

    programming syntax related to function or method declarations in various programming languages.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron identifies programming‐language tokens (e.g. keywords like “return” or “throw,” placeholders like “???,” identifiers such as “y,” and accessors like “get”)—i.e. it flags code elements.

    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
    臆
    -1.03
     maksi
    -1.02
     surpris
    -1.01
     annet
    -0.98
     menn
    -0.98
    chenken
    -0.97
     akku
    -0.97
     SolutionA
    -0.95
    氅
    -0.95
    lesque
    -0.94
    POSITIVE LOGITS
         
    1.01
     know
    0.99
          
    0.98
    It
    0.97
    Pro
    0.94
           
    0.93
     Know
    0.93
     k
    0.92
     //
    0.90
    pro
    0.89
    Activations Density 0.000%

    No Known Activations