© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2768
    Prev
    Next
    INDEX
    Explanations

    courtesy of

    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
    Not in Any Lists

    No Comments

    Negative Logits
     aéreas
    -0.96
     continuare
    -0.96
    Liet
    -0.94
    矬
    -0.94
     cír
    -0.94
    bruik
    -0.93
     části
    -0.92
     qualquer
    -0.92
     версия
    -0.91
     combustível
    -0.91
    POSITIVE LOGITS
     of
    4.22
     the
    1.41
    of
    1.27
    ของ
    1.17
    Of
    1.12
     daripada
    1.11
    ()
    1.08
     verändert
    1.05
     from
    1.05
     olivat
    1.01
    Activations Density 0.015%

    No Known Activations