© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56737
    Prev
    Next
    INDEX
    Explanations

    specific phrases after delimiters

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

    The neuron fires on the “](" sequence that begins a Markdown link or image URL.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     tapping
    -0.83
    ttää
    -0.77
     challeng
    -0.75
    山本
    -0.71
    raiz
    -0.70
     اح
    -0.70
     decorate
    -0.69
     generally
    -0.69
    tament
    -0.69
     Descub
    -0.69
    POSITIVE LOGITS
     '<?
    0.83
    hift
    0.83
     další
    0.82
    gantian
    0.82
     stanga
    0.81
     officiels
    0.79
     fréqu
    0.78
    éndole
    0.77
    '<
    0.77
    MOL
    0.77
    Activations Density 0.000%

    No Known Activations