© 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. 34-GEMMASCOPE-RES-131K
    7. 106148
    Prev
    Next
    INDEX
    Explanations

    numbers, research, code, personal descriptions

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     we
    -1.09
    community
    -0.82
    jointe
    -0.80
     đón
    -0.80
     of
    -0.76
    ೦
    -0.75
     Übernach
    -0.75
     hilsen
    -0.73
    在其
    -0.73
    getContentPane
    -0.71
    POSITIVE LOGITS
     researcher
    1.13
     Researcher
    0.96
     study
    0.90
     pesquisa
    0.89
     أك
    0.87
    Researcher
    0.86
     самы
    0.84
     researchers
    0.82
    LITERATURE
    0.81
     Researchers
    0.80
    Activations Density 0.002%

    No Known Activations