© 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. 90328
    Prev
    Next
    INDEX
    Explanations

    preparation verbs

    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
     you
    -1.65
    を中心に
    -1.48
     levels
    -1.44
    or
    -1.44
     появится
    -1.43
    //
    -1.39
    原本
    -1.39
    この日は
    -1.39
     credi
    -1.38
    }$,
    -1.37
    POSITIVE LOGITS
     sicheren
    1.64
     a
    1.45
     hicieron
    1.40
    maktadır
    1.33
    ziasztok
    1.28
    kanak
    1.27
    rajz
    1.27
    Һ
    1.27
    ISODE
    1.25
     Шта
    1.23
    Activations Density 0.179%

    No Known Activations