© 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. 34-GEMMASCOPE-RES-131K
    7. 92976
    Prev
    Next
    INDEX
    Explanations

    code identifiers and constructs

    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
     tė
    -1.06
     unite
    -1.06
     father
    -1.05
     např
    -1.05
     tzw
    -1.05
     子ども
    -1.02
    numOf
    -0.98
    有钱
    -0.98
     борьбе
    -0.97
     damaligen
    -0.96
    POSITIVE LOGITS
     Agosto
    1.09
    Maybe
    1.09
     Mereka
    1.08
     дола
    1.05
     Kegiatan
    1.02
    Perhaps
    1.01
    defn
    0.99
     Kasus
    0.98
     Makanan
    0.97
     Menggunakan
    0.96
    Activations Density 0.126%

    No Known Activations