© 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. 47797
    Prev
    Next
    INDEX
    Explanations

    names of cities and places

    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
     网络
    -0.82
     saldır
    -0.79
     Comer
    -0.78
     rosado
    -0.78
    瑤
    -0.77
     overseen
    -0.75
     celebrado
    -0.74
    ButtonPressed
    -0.74
    本番
    -0.74
     kept
    -0.73
    POSITIVE LOGITS
    Shipping
    0.91
     Ø
    0.87
     vég
    0.86
    tuuri
    0.85
     وس
    0.84
    shipping
    0.84
    established
    0.84
     canon
    0.83
     $("#
    0.81
    atized
    0.77
    Activations Density 0.013%

    No Known Activations