© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79434
    Prev
    Next
    INDEX
    Explanations

    fossils and evolution

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

    content related to fossils and paleontological time periods.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
    天赋
    -0.83
    ėms
    -0.81
    Kube
    -0.79
     houve
    -0.77
     Aquaculture
    -0.76
     houden
    -0.75
     fertig
    -0.75
     kaart
    -0.75
     '__
    -0.73
    $=
    -0.73
    POSITIVE LOGITS
     fossil
    2.02
     preserved
    1.79
     fossils
    1.56
     records
    1.45
    fossil
    1.45
     record
    1.35
     fossi
    1.33
     preserve
    1.31
     preservation
    1.28
    record
    1.27
    Activations Density 0.070%

    No Known Activations