© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92014
    Prev
    Next
    INDEX
    Explanations

    Homo sapiens evolution

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

    scientific terms related to human evolution, particularly references to Homo sapiens and early human species.

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

    The neuron strongly activates on numeric tokens (especially dates) and Latin taxonomic names (e.g., “Homo sapiens”).

    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
     progettazione
    -0.77
     personal
    -0.77
     Provenance
    -0.76
    ༘
    -0.73
    收到
    -0.73
     Tante
    -0.71
     Soak
    -0.71
     Frucht
    -0.71
     sale
    -0.68
     prakty
    -0.68
    POSITIVE LOGITS
     Homo
    3.02
     homo
    2.80
    Homo
    2.72
    homo
    2.25
     sapiens
    1.98
     Sapi
    1.57
     Hom
    1.30
     HOM
    1.30
     species
    1.27
     hom
    1.16
    Activations Density 0.034%

    No Known Activations