© 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. 63631
    Prev
    Next
    INDEX
    Explanations

    villa and related place names

    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
     metropolitana
    -0.82
     alrededores
    -0.81
     disposent
    -0.80
    ܙ
    -0.75
     berbicara
    -0.73
    albero
    -0.72
     Игорь
    -0.72
     circonst
    -0.72
     consideramos
    -0.71
     اليد
    -0.71
    POSITIVE LOGITS
    gers
    1.02
    ggio
    0.93
    inous
    0.91
    real
    0.88
    gio
    0.83
    罡
    0.82
    馭
    0.81
    سول
    0.81
    بات
    0.79
    GERS
    0.79
    Activations Density 0.018%

    No Known Activations