© 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. 22-GEMMASCOPE-RES-131K
    7. 130334
    Prev
    Next
    INDEX
    Explanations

    The neuron detects numbered reference citations (i.e. isolated digits used as bibliography or footnote markers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    When Hemoglobin Introduction

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

    citation numbers or reference indicators in academic or technical texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    mpto
    -0.96
    kön
    -0.96
     saisi
    -0.94
     then
    -0.94
    ições
    -0.91
    kona
    -0.90
     zakon
    -0.90
     of
    -0.89
    に行きました
    -0.88
    UCION
    -0.86
    POSITIVE LOGITS
    5
    1.12
    I
    1.11
     ponownie
    1.02
    7
    0.97
    8
    0.96
    9
    0.93
    6
    0.85
    ृ
    0.84
     liefern
    0.84
     rất
    0.84
    Activations Density 0.000%

    No Known Activations