© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 7214
    Prev
    Next
    INDEX
    Explanations

    licensed, incorporated, importing

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

    The neuron is triggered by LaTeX “\ce{…}” chemical‐formula markup.

    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
     Harvey
    -0.69
    Curtis
    -0.67
     русской
    -0.67
     учеб
    -0.66
    ern
    -0.63
    ager
    -0.63
     Curtis
    -0.62
     ACP
    -0.61
    dll
    -0.61
     Chia
    -0.61
    POSITIVE LOGITS
    نگار
    0.72
     निय
    0.71
    沿革
    0.70
    μος
    0.70
    Invalidate
    0.70
    ᑐ
    0.69
     Béla
    0.68
     Fernand
    0.68
    couvrez
    0.66
     hostilities
    0.66
    Activations Density 0.054%

    No Known Activations