© 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. 22-GEMMASCOPE-RES-131K
    7. 34135
    Prev
    Next
    INDEX
    Explanations

    cell or cancer following a number

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

    scientific strain designations like cell lines, bacterial strains, and lab specimens in academic papers.

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

    The neuron activates on numeric tokens (digits or numeric measurements) in scientific text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     különböző
    -1.24
     meestal
    -1.16
     mereka
    -1.15
     обычно
    -1.13
    往往
    -1.10
     genellikle
    -1.09
     scattata
    -1.07
     różne
    -1.07
     varying
    -1.06
     espaços
    -1.06
    POSITIVE LOGITS
     Վերցված
    0.99
     has
    0.97
     having
    0.97
     SUPPLIES
    0.96
    छे
    0.96
     kita
    0.96
     we
    0.94
    侷
    0.94
    Похо
    0.93
     interiores
    0.93
    Activations Density 0.084%

    No Known Activations