© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 162
    Prev
    Next
    INDEX
    Explanations

    local 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_10/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
     what
    -2.27
     to
    -1.60
     their
    -1.50
    {
    -1.45
     eight
    -1.45
     before
    -1.43
     Before
    -1.41
     six
    -1.38
     nine
    -1.38
     three
    -1.35
    POSITIVE LOGITS
     andere
    1.48
    wherein
    1.38
     chercheurs
    1.38
     autres
    1.38
    ньому
    1.35
     œufs
    1.34
     huiles
    1.34
    atized
    1.30
     カットソー
    1.29
     других
    1.28
    Activations Density 0.088%

    No Known Activations