© 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. 32690
    Prev
    Next
    INDEX
    Explanations

    past actions or states

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

    The neuron activates on numeric/statistical expressions (digits and their immediate context), i.e. counts, ages, percentages, and related tokens in result‐reporting or data‐reporting passages.

    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
     it
    -1.46
     here
    -1.46
     sigue
    -1.24
     everything
    -1.24
     everyone
    -1.17
     requisitos
    -1.17
     that
    -1.16
     paciencia
    -1.16
     agli
    -1.16
    人也
    -1.15
    POSITIVE LOGITS
    🗝
    1.26
    因為
    1.24
     pesta
    1.23
     actrices
    1.23
     Kristus
    1.20
     사용
    1.20
     Paket
    1.20
     vokal
    1.19
     активно
    1.19
    gingen
    1.19
    Activations Density 0.099%

    No Known Activations