© 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. 55890
    Prev
    Next
    INDEX
    Explanations

    tree rings, chronology, paleoclimate

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

    content related to tree rings and dendrochronology research.

    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
     tiêu
    -0.84
    ticia
    -0.75
     senare
    -0.75
     Hammond
    -0.73
     Honey
    -0.71
     Mink
    -0.71
     열
    -0.70
    iben
    -0.68
     Benton
    -0.68
    ukas
    -0.68
    POSITIVE LOGITS
     ring
    1.20
     dend
    1.08
    rings
    0.98
    dend
    0.96
     tree
    0.95
     bristle
    0.93
     rings
    0.93
    Rings
    0.92
     chronology
    0.91
    ring
    0.89
    Activations Density 0.020%

    No Known Activations