© 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. 58122
    Prev
    Next
    INDEX
    Explanations

    hoping for something

    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
     \
    -2.06
    ଽ
    -1.98
     ४
    -1.89
    Surprisingly
    -1.87
     bernama
    -1.77
    arán
    -1.77
    所谓的
    -1.77
     Viernes
    -1.69
    nachron
    -1.66
    ῖ
    -1.66
    POSITIVE LOGITS
     a
    3.23
    "
    2.39
     "
    1.91
     The
    1.85
     
    1.81
    ното
    1.76
    ".
    1.72
     We
    1.71
    ,.
    1.71
    {
    1.68
    Activations Density 0.008%

    No Known Activations