© 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. 34-GEMMASCOPE-RES-131K
    7. 93340
    Prev
    Next
    INDEX
    Explanations

    /* comments or code header

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

    The neuron is specialized to detect comment-terminator tokens (the “*/” that ends block 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_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
     in
    -1.11
     usually
    -1.09
     for
    -1.05
     an
    -0.94
     (
    -0.93
     Usually
    -0.93
     or
    -0.93
     same
    -0.91
    silience
    -0.90
    ,
    -0.89
    POSITIVE LOGITS
    varande
    1.18
    ↵
    1.14
    螃
    1.08
     ancor
    1.05
     cioc
    1.05
     interessa
    0.99
     feltro
    0.99
     disposto
    0.98
     delightfully
    0.98
     lond
    0.97
    Activations Density 0.027%

    No Known Activations