© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77042
    Prev
    Next
    INDEX
    Explanations

    place names and locations

    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
     natt
    -0.84
     Lach
    -0.79
     Harz
    -0.78
    Lach
    -0.75
    zeria
    -0.74
    ngay
    -0.71
     BIN
    -0.70
    TableViewCell
    -0.69
    julia
    -0.67
    พิ
    -0.67
    POSITIVE LOGITS
    Rochester
    1.24
     Rochester
    1.20
     Mayo
    1.09
    Mayo
    1.05
    mayo
    0.87
    esseur
    0.84
     Winona
    0.82
     mayo
    0.81
    Minnesota
    0.79
    ✵
    0.77
    Activations Density 0.010%

    No Known Activations