© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91351
    Prev
    Next
    INDEX
    Explanations

    biological cells and tissues

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

    This neuron detects cell culture and laboratory cell line references in scientific/biological contexts.

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

    The neuron strongly responds to terms that describe experimental methods or protocols (e.g. “using,” “in,” “cells,” “growing,” “employed”), i.e. it flags sections detailing laboratory procedures.

    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
    koma
    -0.78
     pathogens
    -0.77
     facing
    -0.70
     shelter
    -0.68
    TempData
    -0.68
    着用
    -0.67
     stared
    -0.66
    ませんか
    -0.66
    ჟ
    -0.66
     shel
    -0.65
    POSITIVE LOGITS
     cells
    1.20
     cell
    1.19
    cells
    1.11
     Cells
    1.01
    cell
    1.01
     eukaryotic
    0.90
     susceptible
    0.89
    Cell
    0.87
    细胞
    0.87
     Vero
    0.87
    Activations Density 0.189%

    No Known Activations