© 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. 3263
    Prev
    Next
    INDEX
    Explanations

    figure and table labels

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

    The neuron detects numbered references to figures, tables, schemes, or similar labeled elements 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
     eighty
    -1.19
     sixty
    -1.18
     seventy
    -1.14
    Sixty
    -1.12
     fifty
    -0.97
     Seventy
    -0.95
     forty
    -0.95
     thirty
    -0.95
     ninety
    -0.94
     Sixty
    -0.93
    POSITIVE LOGITS
     ثلاثة
    0.85
     één
    0.82
    μία
    0.80
     gobierno
    0.80
     III
    0.80
     первом
    0.78
     deux
    0.76
    彼
    0.76
     II
    0.75
     enkele
    0.75
    Activations Density 0.024%

    No Known Activations