© 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. 1010
    Prev
    Next
    INDEX
    Explanations

    microcontrollers and motor modules

    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
     on
    -1.70
     not
    -1.68
     after
    -1.65
     more
    -1.65
     going
    -1.60
    ִּ
    -1.51
     taking
    -1.48
     only
    -1.47
     because
    -1.47
     rowspan
    -1.45
    POSITIVE LOGITS
     绘画
    1.62
     الجلد
    1.55
    ِّ
    1.52
     tampaknya
    1.48
    愜
    1.48
     头像
    1.45
     sentimentos
    1.45
     sostu
    1.44
    キレイ
    1.42
     flexibilidad
    1.41
    Activations Density 0.321%

    No Known Activations