© 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. 98448
    Prev
    Next
    INDEX
    Explanations

    digital identifiers

    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
     their
    -1.11
     Volkes
    -0.93
     various
    -0.90
     probably
    -0.79
     many
    -0.79
    させて頂きます
    -0.79
     whoever
    -0.78
     curriculum
    -0.75
    劵
    -0.74
    lccc
    -0.73
    POSITIVE LOGITS
    resized
    0.80
     pertinente
    0.79
     tamaño
    0.77
     republi
    0.75
    ляется
    0.75
    aquí
    0.74
    WAITING
    0.73
    delicious
    0.73
    toj
    0.72
    tamanho
    0.71
    Activations Density 0.027%

    No Known Activations