© 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. 116235
    Prev
    Next
    INDEX
    Explanations

    programming element constructs

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

    The neuron spikes whenever the token “Element” (in any casing, e.g. ELEMENT) appears in the text.

    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
    hmigung
    -0.80
    olt
    -0.77
     Ballon
    -0.75
     huo
    -0.74
     тот
    -0.72
    мені
    -0.72
     tham
    -0.72
     وظ
    -0.71
     Further
    -0.69
    狱
    -0.69
    POSITIVE LOGITS
    ulisan
    0.87
     acrí
    0.82
    UTM
    0.81
    موس
    0.81
     innymi
    0.80
    😌
    0.78
    »?
    0.78
     元素
    0.77
     recargable
    0.76
     vzduchu
    0.76
    Activations Density 0.014%

    No Known Activations