© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128279
    Prev
    Next
    INDEX
    Explanations

    sending or communicating

    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
     I
    -1.61
     we
    -1.52
    ’
    -1.46
    六年
    -1.39
     “
    -1.32
     bądź
    -1.32
     \
    -1.29
     vaak
    -1.28
     друзей
    -1.27
     zdjęcie
    -1.23
    POSITIVE LOGITS
    的基本
    1.45
    嘮
    1.44
    子供が
    1.39
    夕食
    1.38
    ⌗
    1.37
     besök
    1.36
    始化
    1.36
    夕方
    1.35
     kimdir
    1.34
     magasiner
    1.33
    Activations Density 0.118%

    No Known Activations