© 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. 118048
    Prev
    Next
    INDEX
    Explanations

    Nature journal citations

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

    citations from academic journals, particularly Nature journal.

    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_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
    haustible
    -0.92
     佳
    -0.78
     istället
    -0.75
    bookings
    -0.74
     which
    -0.74
    =@
    -0.74
    tvrt
    -0.73
    ambig
    -0.72
    спу
    -0.71
     Regel
    -0.71
    POSITIVE LOGITS
    Nature
    1.44
     Nature
    1.42
     nature
    1.15
    nature
    1.13
     NATURE
    1.09
     Natur
    0.97
    Science
    0.96
    NATURE
    0.96
    Natur
    0.95
     science
    0.91
    Activations Density 0.016%

    No Known Activations