© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13583
    Prev
    Next
    INDEX
    Explanations

    unpublished United States court documents

    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
    izator
    -1.34
    dreaming
    -1.27
    hörer
    -1.27
     vocale
    -1.25
     목록
    -1.24
     tahun
    -1.23
    bathing
    -1.23
     rainha
    -1.20
    無線
    -1.20
     mesto
    -1.20
    POSITIVE LOGITS
    f
    1.48
    ↵
    1.28
    </h1>
    1.27
     évek
    1.24
     bisiklet
    1.21
     ggf
    1.20
    ore
    1.18
    —
    1.18
    teal
    1.13
     dirigir
    1.13
    Activations Density 0.018%

    No Known Activations