© 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. 103782
    Prev
    Next
    INDEX
    Explanations

    place names and transport infrastructure

    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
     Maren
    -0.80
     bayer
    -0.77
    onResume
    -0.73
    PIER
    -0.70
     satisfied
    -0.68
    肤
    -0.67
     pastic
    -0.66
     Catan
    -0.66
     gothic
    -0.65
     intimately
    -0.65
    POSITIVE LOGITS
     Newport
    1.71
    Newport
    1.48
     Monmouth
    1.23
    Cw
    0.86
     Cebu
    0.85
    autoComplete
    0.85
     esquerda
    0.85
     père
    0.82
     Cardiff
    0.81
     Middletown
    0.79
    Activations Density 0.022%

    No Known Activations