© 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. 21168
    Prev
    Next
    INDEX
    Explanations

    it was that

    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
     thre
    -1.48
     ebenfalls
    -1.41
    ﺪ
    -1.39
    意思是
    -1.37
     dring
    -1.35
    Ꮻ
    -1.34
    ーと
    -1.34
     sach
    -1.33
     too
    -1.32
     umgangssprach
    -1.32
    POSITIVE LOGITS
     will
    1.77
     your
    1.73
     that
    1.66
     nantinya
    1.66
     with
    1.49
    !（
    1.40
     będziemy
    1.39
     beserta
    1.38
     sprawie
    1.35
    контро
    1.33
    Activations Density 0.013%

    No Known Activations