© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78211
    Prev
    Next
    INDEX
    Explanations

    extinct genera and species

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

    scientific or paleontological content about fossils and extinct species from geological formations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on official conservation or geological designation phrases (e.g. “Site of Special Scientific Interest,” “Geological Conservation Review site”).

    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
    poro
    -0.88
     dahulu
    -0.73
     branches
    -0.73
     read
    -0.73
     Genti
    -0.72
    CONN
    -0.71
    HandleFunc
    -0.70
    ittar
    -0.70
     Archaeology
    -0.70
     hẳn
    -0.70
    POSITIVE LOGITS
     localities
    1.19
     fossil
    1.16
     locality
    1.09
     exposures
    1.05
     fossils
    0.99
    locality
    0.94
    เก็บ
    0.88
    fossil
    0.88
     Fossil
    0.87
     horizons
    0.86
    Activations Density 0.034%

    No Known Activations