© 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. 47569
    Prev
    Next
    INDEX
    Explanations

    reason for or of

    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
     encantador
    -2.23
     animados
    -2.13
     viviendas
    -2.08
    इटम
    -2.03
     tugas
    -2.02
    Ⅲ
    -2.00
    喾
    -1.91
     Gunakan
    -1.88
     perdidos
    -1.88
    Balancer
    -1.85
    POSITIVE LOGITS
    ar
    2.84
     why
    2.59
    at
    2.30
    in
    2.25
    2
    2.16
     reason
    2.03
    ab
    2.02
    ak
    1.96
    0
    1.96
    在他的
    1.94
    Activations Density 0.050%

    No Known Activations