© 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. 10-GEMMASCOPE-RES-131K
    7. 111053
    Prev
    Next
    INDEX
    Explanations

    my, your, our possessions

    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
    There
    -1.62
    发了
    -1.45
    Those
    -1.43
    𝚣
    -1.41
     таких
    -1.41
     такого
    -1.40
     такой
    -1.39
    君は
    -1.38
     после
    -1.37
     entrepre
    -1.34
    POSITIVE LOGITS
     about
    1.84
     the
    1.82
     a
    1.50
     they
    1.45
    </i>
    1.40
     instead
    1.36
     Instead
    1.34
     vastly
    1.32
    媲
    1.31
     immense
    1.30
    Activations Density 0.094%

    No Known Activations