© 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. 34-GEMMASCOPE-RES-131K
    7. 90902
    Prev
    Next
    INDEX
    Explanations

    place names and institutions

    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
     Koko
    -1.02
    Koko
    -0.91
    blumen
    -0.82
    ICHT
    -0.81
    mitteilung
    -0.80
     unik
    -0.79
    gangs
    -0.79
     Fj
    -0.78
    character
    -0.75
     jälkeen
    -0.75
    POSITIVE LOGITS
     Danville
    1.36
     wą
    0.72
     statt
    0.72
    hemis
    0.69
     postav
    0.69
    noks
    0.69
    ਢ
    0.68
     paste
    0.68
    allon
    0.68
     chicago
    0.67
    Activations Density 0.010%

    No Known Activations