© 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. 10-GEMMASCOPE-RES-131K
    4. 19561
    Prev
    Next
    INDEX
    Explanations

    noun phrases

    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
     Itali
    -1.58
     is
    -1.48
    fying
    -1.42
    erst
    -1.35
    act
    -1.34
    zed
    -1.33
    还想
    -1.33
    *
    -1.28
    却被
    -1.27
    是一個
    -1.27
    POSITIVE LOGITS
     who
    2.22
     for
    1.98
     on
    1.96
     that
    1.95
     with
    1.85
     which
    1.80
     whose
    1.77
     at
    1.63
     those
    1.61
     these
    1.55
    Activations Density 0.234%

    No Known Activations