© 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. 22-GEMMASCOPE-RES-131K
    4. 36063
    Prev
    Next
    INDEX
    Explanations

    units and scientific notation

    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_22/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
    -2.42
    ところに
    -1.63
     from
    -1.63
    の方に
    -1.63
     their
    -1.63
    に行って
    -1.62
    の準備
    -1.61
    を目指す
    -1.57
     that
    -1.55
    ****
    -1.55
    POSITIVE LOGITS
    を
    2.31
    もあって
    1.96
    が
    1.91
    ztes
    1.86
    そして
    1.85
    と
    1.80
    <bos>
    1.80
    で
    1.79
    がありますが
    1.78
    も
    1.75
    Activations Density 0.056%

    No Known Activations