© 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. 57707
    Prev
    Next
    INDEX
    Explanations

    Bradford Lowry method

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

    citations and references in scientific papers, particularly focusing on methodology sections and author attributions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is primarily detecting numerical tokens (digits and numeric strings such as years, volumes, section numbers, and reference markers).

    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
     PRESENTATION
    -0.80
     naszego
    -0.79
     Präsentation
    -0.78
     kostenlosen
    -0.77
    aston
    -0.73
    ecture
    -0.73
    elas
    -0.73
    tians
    -0.72
    atelle
    -0.72
    ぼく
    -0.71
    POSITIVE LOGITS
     Samb
    1.68
     Bradford
    1.49
    Bradford
    1.38
     Liv
    1.34
     Chom
    1.17
     Lowry
    1.11
     method
    1.10
    Liv
    1.08
     methods
    1.08
     Mani
    1.01
    Activations Density 0.039%

    No Known Activations