© 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. 10-GEMMASCOPE-RES-131K
    7. 130059
    Prev
    Next
    INDEX
    Explanations

    BY followed by names or programming annotations

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

    The neuron identifies uppercase “BY” lines that introduce an article’s byline (author credit).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    h
    -1.43
    f
    -1.29
    is
    -1.24
     notwendigen
    -1.23
    lo
    -1.19
     used
    -1.17
     betreffenden
    -1.16
    mp
    -1.16
     (“
    -1.15
    ch
    -1.14
    POSITIVE LOGITS
    Sighs
    1.36
    colori
    1.34
     başarılı
    1.30
    endaftar
    1.28
     he
    1.27
    vård
    1.26
    batik
    1.23
    嚯
    1.21
     dönem
    1.19
     感じ
    1.18
    Activations Density 0.233%

    No Known Activations