© 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. 99496
    Prev
    Next
    INDEX
    Explanations

    people's names and citations

    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
     همه
    -1.39
     ولكن
    -1.24
    !」
    -1.23
    ід
    -1.21
     semua
    -1.20
     tarte
    -1.17
    </h3>
    -1.16
    時間
    -1.14
     balancer
    -1.14
    所有
    -1.13
    POSITIVE LOGITS
    </b>
    1.44
     already
    1.41
     muhimu
    1.36
     a
    1.34
     these
    1.27
    ໊
    1.27
    hướng
    1.26
     inaweza
    1.26
    灯光
    1.25
     campuran
    1.23
    Activations Density 0.213%

    No Known Activations