© 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. 10004
    Prev
    Next
    INDEX
    Explanations

    'and' followed by other items

    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
     and
    -2.19
     is
    -2.08
     was
    -1.92
    There
    -1.77
     should
    -1.73
     first
    -1.72
    What
    -1.61
     only
    -1.59
    Getting
    -1.55
     two
    -1.54
    POSITIVE LOGITS
     fiables
    1.84
     refugi
    1.78
    镞
    1.74
    䜣
    1.72
    ఽ
    1.72
    ção
    1.72
    螃
    1.65
    ︲
    1.65
     evangé
    1.63
    ☫
    1.62
    Activations Density 0.041%

    No Known Activations