© 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. 22660
    Prev
    Next
    INDEX
    Explanations

    variables influencing outcomes

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

    The neuron is highly selective for the word “variable” (and its plural form “variables”) in technical or scientific contexts.

    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
     Anſ
    -2.44
     ‘’
    -2.41
     Perſ
    -2.22
    ’
    -2.20
     Inſ
    -2.20
     Diſ
    -2.19
    撄
    -2.17
    sandalia
    -2.16
     Reſ
    -2.14
     Eſ
    -2.08
    POSITIVE LOGITS
    蛧
    2.36
     でも
    2.19
     our
    2.17
     burgeoning
    2.17
     longtime
    2.13
     any
    2.06
    !!!!!
    2.02
    From
    1.98
     in
    1.96
     incorporate
    1.94
    Activations Density 0.025%

    No Known Activations