© 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. 130554
    Prev
    Next
    INDEX
    Explanations

    BNI, BioConnect, Electro Rent, approval

    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
    因為
    -1.88
     kathol
    -1.51
     Pfar
    -1.46
    wherein
    -1.45
     ricas
    -1.45
    有一些
    -1.44
     people
    -1.44
    เพราะ
    -1.41
     cukru
    -1.41
     repente
    -1.41
    POSITIVE LOGITS
    ૉ
    2.23
    챕
    1.91
     inmiddels
    1.80
    战术
    1.77
    ̀nh
    1.72
    謠
    1.70
     грамм
    1.70
    ệu
    1.65
    歿
    1.63
     cirugía
    1.60
    Activations Density 0.162%

    No Known Activations