© 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. 22-GEMMASCOPE-RES-131K
    7. 32803
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    The neuron strongly activates on numeric literals (especially decimal or floating‐point numbers).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ofrece
    -1.11
     mediante
    -1.09
     ベクトル
    -1.05
     diversos
    -1.03
    可谓
    -1.02
     paltry
    -1.01
     joyous
    -1.00
     lamentable
    -0.99
     grandiose
    -0.99
     bijna
    -0.98
    POSITIVE LOGITS
     because
    1.24
     enthusiastic
    1.23
    أك
    1.12
     kritik
    1.11
     eager
    1.11
     publik
    1.10
    telles
    1.06
    avoit
    1.05
    zku
    1.05
    kursi
    1.05
    Activations Density 0.092%

    No Known Activations