© 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. 58031
    Prev
    Next
    INDEX
    Explanations

    USA

    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
    ####
    -0.91
    　　“
    -0.90
    umid
    -0.85
     defi
    -0.81
    hamdulillah
    -0.77
    leetcode
    -0.75
     guineas
    -0.74
     systolic
    -0.73
     söyl
    -0.73
     towel
    -0.73
    POSITIVE LOGITS
     USA
    1.06
    USA
    0.91
    ►
    0.80
    ginous
    0.80
     establece
    0.78
     можливо
    0.77
     Usa
    0.75
     manchen
    0.75
    gan
    0.74
    DataBean
    0.74
    Activations Density 0.030%

    No Known Activations