© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32998
    Prev
    Next
    INDEX
    Explanations

    markup tags and code

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

    The neuron is selectively firing on formatting and markup tokens—things like punctuation hyphens, angle‐bracket tags (e.g. `<pre…>`), code/map markers, and other structural or markup constructs rather than ordinary words.

    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
     discurso
    -0.84
    arna
    -0.82
    ]();
    -0.72
    ерез
    -0.72
     Serving
    -0.72
    quiagem
    -0.71
    uckt
    -0.70
    paramMap
    -0.70
    otor
    -0.69
     wz
    -0.68
    POSITIVE LOGITS
     <
    1.08
    ("<
    0.99
    ><
    0.97
    +<
    0.96
    .<
    0.93
    ('<
    0.93
    ()<
    0.92
    ,<
    0.91
     $<$
    0.91
     $<
    0.88
    Activations Density 0.280%

    No Known Activations