© 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. 64150
    Prev
    Next
    INDEX
    Explanations

    Histologic, Tennessee State

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

    The neuron selectively fires on typographical section headings and formal structural labels (e.g. “Background,” “Method,” boldfaced title fragments, numbered section markers) in academic‐paper layouts.

    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
     draft
    -0.81
    罄
    -0.77
     drafts
    -0.69
    ұ
    -0.68
    DRAFT
    -0.68
    thr
    -0.67
    ‣
    -0.67
    🐖
    -0.67
     Editable
    -0.67
     merchants
    -0.67
    POSITIVE LOGITS
     ghosts
    0.99
     ghost
    0.99
    Ghost
    0.92
     Ghost
    0.90
     antig
    0.86
    variation
    0.86
    Variation
    0.84
     Grass
    0.84
     Variation
    0.84
     variation
    0.83
    Activations Density 0.013%

    No Known Activations