© 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. 114157
    Prev
    Next
    INDEX
    Explanations

    counting words

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

    numeric values in lists or sequences, particularly when describing quantities, measurements, or procedural steps.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @bfgcn7frf5
    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
     who
    -1.70
     razões
    -1.33
     nécessité
    -1.29
     которы
    -1.27
     possibilidades
    -1.25
     people
    -1.24
     Dumnezeu
    -1.23
     dúvidas
    -1.20
    фотография
    -1.20
     fora
    -1.20
    POSITIVE LOGITS
     such
    1.63
     or
    1.50
      
    1.30
     sélections
    1.25
    其它
    1.20
    Život
    1.19
     each
    1.17
    ”？
    1.16
     undertaken
    1.16
     session
    1.16
    Activations Density 0.442%

    No Known Activations