© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 66133
    Prev
    Next
    INDEX
    Explanations

    Japanese 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
     new
    -0.97
    josh
    -0.90
     Mindest
    -0.87
     Quite
    -0.84
     zależ
    -0.83
     entitled
    -0.81
     Sub
    -0.81
    祟
    -0.81
    razer
    -0.81
     Non
    -0.78
    POSITIVE LOGITS
     speciali
    1.01
    關於
    0.97
    还不错
    0.95
    ここでは
    0.92
    respectively
    0.91
    ︐
    0.90
     respec
    0.90
    anabe
    0.88
    took
    0.88
     infinit
    0.87
    Activations Density 0.004%

    No Known Activations