© 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. 22-GEMMASCOPE-RES-131K
    7. 27470
    Prev
    Next
    INDEX
    Explanations

    stone flaming

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

    The neuron fires on the Markdown image‐embed syntax (the “![…](…)” pattern used for badges like Build Status).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     also
    -0.88
    циони
    -0.81
     jej
    -0.79
    boy
    -0.79
    ingan
    -0.79
    országban
    -0.79
     cubo
    -0.79
    於
    -0.78
     расходы
    -0.78
     ayrıca
    -0.78
    POSITIVE LOGITS
     that
    1.07
     dầu
    0.86
    Bekijk
    0.85
     "','
    0.85
    editorial
    0.84
     Wartawan
    0.83
     düğ
    0.82
    ousel
    0.82
    Wanneer
    0.82
     hört
    0.81
    Activations Density 0.001%

    No Known Activations