© 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. 68721
    Prev
    Next
    INDEX
    Explanations

    held my tongue

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    .
    -1.76
     после
    -1.50
    珰
    -1.49
     depois
    -1.47
     two
    -1.47
    इटम
    -1.46
    enfone
    -1.45
     to
    -1.45
     allegedly
    -1.43
    neling
    -1.41
    POSITIVE LOGITS
     against
    1.59
     stren
    1.57
    8
    1.45
    icação
    1.41
    2
    1.40
    \
    1.38
    4
    1.37
     imm
    1.36
     intel
    1.33
     in
    1.29
    Activations Density 0.009%

    No Known Activations