© 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. 10-GEMMASCOPE-RES-131K
    7. 38986
    Prev
    Next
    INDEX
    Explanations

    fossils and ancient life descriptions

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

    paleontological and archaeological content about extinct species, fossils, and prehistoric discoveries.

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

    The neuron detects scientific taxon names, especially genus names (often Latin binomials) in descriptions of extinct or extant organisms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     each
    -1.74
    ּוֹ
    -1.72
     inmig
    -1.52
    篆
    -1.46
     agricultura
    -1.44
     accion
    -1.37
    諳
    -1.34
    旰
    -1.32
     Química
    -1.32
     AQUÍ
    -1.31
    POSITIVE LOGITS
     Hinsicht
    1.54
     that
    1.51
     berbahaya
    1.47
     даже
    1.46
     rapporti
    1.35
    Additionally
    1.34
    さらに
    1.31
     вместо
    1.28
     entonces
    1.27
    ꒳
    1.23
    Activations Density 0.100%

    No Known Activations