© 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. 34-GEMMASCOPE-RES-131K
    7. 77488
    Prev
    Next
    INDEX
    Explanations

    code block terminators or headers

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

    This neuron detects boilerplate header and metadata tokens (e.g. auto-generated notices, license comments, configuration directives) in code or markup files.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     dolar
    -0.90
     uska
    -0.87
     Azul
    -0.86
     boh
    -0.85
     BIRTHDAY
    -0.84
     tirs
    -0.84
     ople
    -0.83
     hunde
    -0.83
    🎣
    -0.81
     herre
    -0.81
    POSITIVE LOGITS
    return
    0.90
    pão
    0.88
     family
    0.82
    斤
    0.82
     tuck
    0.82
     must
    0.76
     Ins
    0.75
     этих
    0.74
     instead
    0.73
     is
    0.72
    Activations Density 0.002%

    No Known Activations