© 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. 39307
    Prev
    Next
    INDEX
    Explanations

    reports and related actions

    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
    ׇ
    -2.30
     گیاه
    -2.17
    Although
    -1.95
     chré
    -1.95
     растений
    -1.86
    思議
    -1.84
     cukru
    -1.81
     الجلد
    -1.71
    Despite
    -1.70
     pidana
    -1.65
    POSITIVE LOGITS
     you
    1.96
     its
    1.88
     it
    1.86
    ִּ
    1.82
    ּוֹ
    1.77
     السياس
    1.77
    וּ
    1.67
     last
    1.61
     бампер
    1.61
    ҉
    1.56
    Activations Density 0.284%

    No Known Activations