© 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. 7091
    Prev
    Next
    INDEX
    Explanations

    number sequences

    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
     other
    -0.87
     multiple
    -0.83
    avadoc
    -0.81
    側は
    -0.81
     without
    -0.80
     hor
    -0.79
    KW
    -0.78
    ціа
    -0.77
     современного
    -0.76
     many
    -0.76
    POSITIVE LOGITS
    Zdroj
    1.05
    こんな
    0.90
     blindly
    0.88
    HEET
    0.88
    meyi
    0.87
    )\\
    0.87
    久しぶり
    0.82
    Rptr
    0.82
    gzip
    0.81
     risques
    0.81
    Activations Density 0.001%

    No Known Activations