© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6668
    Prev
    Next
    INDEX
    Explanations

    in a

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

    The neuron responds to numeric expressions and measurement values in the text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    pergillus
    -1.65
     that
    -1.65
    poptotic
    -1.63
    soon
    -1.58
    bestos
    -1.56
    corbic
    -1.51
    cive
    -1.47
    砗
    -1.46
    complished
    -1.46
     セン
    -1.46
    POSITIVE LOGITS
     a
    2.38
     werdet
    1.62
     by
    1.59
     schützen
    1.52
     an
    1.52
    上記
    1.51
     two
    1.48
     ändert
    1.48
     ولكن
    1.44
     fortsetter
    1.41
    Activations Density 0.141%

    No Known Activations