© 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. 34-GEMMASCOPE-RES-131K
    7. 32280
    Prev
    Next
    INDEX
    Explanations

    attributes and values

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

    The neuron detects the SVG XML namespace declaration (e.g. the “http://www.w3.org/2000/svg” URI in an SVG tag).

    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
     getConnection
    -0.78
    Prova
    -0.77
     Pasir
    -0.75
     tối
    -0.73
     came
    -0.71
     big
    -0.71
     Seti
    -0.70
    毅
    -0.70
    といけない
    -0.69
    dft
    -0.69
    POSITIVE LOGITS
    이는
    0.85
    estand
    0.77
    rza
    0.76
    melons
    0.76
    currentColor
    0.76
     feveral
    0.75
    ocument
    0.74
    积分
    0.74
     lädt
    0.74
     rangi
    0.73
    Activations Density 0.021%

    No Known Activations