© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 4315
    Prev
    Next
    INDEX
    Explanations

    academic physics departments and software licenses

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

    The neuron detects bibliography‐style or author‐affiliation markup in academic papers—e.g. footnote/citation markers and department‐of-Physics affiliation lines.

    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
    PhysRev
    -0.88
    ＝
    -0.71
    エディ
    -0.70
    Caleb
    -0.69
    Đăng
    -0.68
    uhkan
    -0.67
    Disappear
    -0.67
    zió
    -0.66
    alleri
    -0.66
     Caleb
    -0.66
    POSITIVE LOGITS
    assure
    0.92
     nuclé
    0.89
     dzien
    0.88
    ausea
    0.80
    ppell
    0.78
    $|
    0.77
     carbide
    0.76
    untung
    0.75
     Coinbase
    0.75
     arbre
    0.74
    Activations Density 0.013%

    No Known Activations