© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22331
    Prev
    Next
    INDEX
    Explanations

    United States

    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
    Not in Any Lists

    No Comments

    Negative Logits
     bluz
    -2.30
    ཫ
    -2.20
     balkon
    -2.17
     唯美
    -2.08
     pittores
    -2.06
    ㍑
    -2.06
     abstrak
    -2.05
    ఌ
    -2.05
     italiens
    -2.05
    kleber
    -2.05
    POSITIVE LOGITS
    :
    2.53
     this
    2.36
     always
    2.23
     for
    2.23
     still
    2.17
    ;
    2.13
     
    2.09
    {
    2.06
    =
    2.05
     like
    2.02
    Activations Density 0.213%

    No Known Activations