© 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. 10154
    Prev
    Next
    INDEX
    Explanations

    letters and position

    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
    ּוֹ
    -1.54
    ֶּ
    -1.54
    ַּ
    -1.53
    signable
    -1.35
     موبایل
    -1.29
     Alamofire
    -1.28
    hever
    -1.27
    matical
    -1.25
     població
    -1.24
    unner
    -1.23
    POSITIVE LOGITS
     are
    1.52
     each
    1.43
     katholischen
    1.42
     Unterstüt
    1.27
     verheir
    1.24
     christlichen
    1.21
     MANY
    1.19
     Каждый
    1.17
     württemberg
    1.16
     that
    1.16
    Activations Density 0.125%

    No Known Activations