© 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. 1860
    Prev
    Next
    INDEX
    Explanations

    macroblock, GOP, picture

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

    The neuron fires on tokens common in software‐license and code‐header boilerplate (e.g. “/”, “modify”, “version”, URLs, and related legal terms).

    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
    emic
    -0.80
     jurisdictional
    -0.75
     غ
    -0.75
     الكريم
    -0.74
     campaign
    -0.74
    randir
    -0.74
     organic
    -0.73
     dove
    -0.71
    igny
    -0.71
    Pinch
    -0.71
    POSITIVE LOGITS
     QP
    0.98
     picture
    0.94
     NAL
    0.92
    NAL
    0.90
     frame
    0.88
    Macro
    0.88
    GOP
    0.88
     GOP
    0.86
     Macro
    0.85
     pictures
    0.84
    Activations Density 0.030%

    No Known Activations