© 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. 14167
    Prev
    Next
    INDEX
    Explanations

    documentation tags

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

    This neuron detects documentation‐comment syntax markers (e.g. the leading asterisks and “@” tags) in source-code comments.

    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
     even
    -1.32
     what
    -1.09
     many
    -1.02
     get
    -1.01
     big
    -1.00
     first
    -0.99
     same
    -0.99
     Even
    -0.98
     earlier
    -0.97
     different
    -0.92
    POSITIVE LOGITS
     odeur
    1.07
     importado
    1.02
     boken
    0.99
     inmigrantes
    0.98
    艄
    0.97
     alarma
    0.97
    braten
    0.97
     sores
    0.96
     déclaration
    0.96
    ירים
    0.95
    Activations Density 0.038%

    No Known Activations