© 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. 119928
    Prev
    Next
    INDEX
    Explanations

    aims to verb

    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
    nitř
    -2.03
     柄
    -1.87
    gencias
    -1.83
    pecabe
    -1.77
     巾
    -1.77
    圌
    -1.76
    ktionen
    -1.73
    igua
    -1.73
     núcleos
    -1.73
     focuses
    -1.72
    POSITIVE LOGITS
    </b>
    1.92
    {
    1.68
    你
    1.48
     соответ
    1.44
     людей
    1.40
    situ
    1.38
    〼
    1.36
     missione
    1.34
    我的
    1.32
    至少
    1.32
    Activations Density 0.027%

    No Known Activations