© 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. 72734
    Prev
    Next
    INDEX
    Explanations

    code comments, metadata, docs

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

    The neuron detects documentation annotations inside comments—i.e. tokens beginning with “@” (like @see, @param, @group, @ref, etc.).

    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
     ultima
    -0.96
    мм
    -0.94
     either
    -0.91
     last
    -0.90
    
    -0.89
    поги
    -0.88
     Siria
    -0.88
     details
    -0.88
     copia
    -0.87
    foam
    -0.87
    POSITIVE LOGITS
     and
    1.53
     passée
    0.97
    Эта
    0.95
     bewerten
    0.94
    alyptus
    0.94
     內
    0.90
    gridColumn
    0.90
     dáms
    0.89
     risol
    0.89
    жением
    0.88
    Activations Density 0.005%

    No Known Activations