© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40604
    Prev
    Next
    INDEX
    Explanations

    biological and chemical entities

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

    terms related to physical body parts and biological structures, particularly in scientific or medical contexts.

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

    The neuron selectively activates on technical scientific or biomedical entity nouns—especially compound terms naming study subjects or materials (e.g. “animal,” “whole‐body,” “small molecule,” “white matter,” “small vessel”).

    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
     pestañas
    -1.72
     coté
    -1.64
    还未
    -1.55
     coreano
    -1.54
     zobac
    -1.54
    ՚
    -1.53
     africano
    -1.53
     pirata
    -1.51
    並不是
    -1.45
     plegable
    -1.43
    POSITIVE LOGITS
     to
    1.73
    防守
    1.61
     and
    1.56
     '
    1.53
    它的
    1.51
    天生
    1.47
    kube
    1.44
     různ
    1.43
    ++,
    1.42
    !"
    1.40
    Activations Density 0.166%

    No Known Activations