© 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. 12128
    Prev
    Next
    INDEX
    Explanations

    position or outcome

    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
     know
    -1.60
     tremend
    -1.46
     essencial
    -1.42
    خاذ
    -1.36
    了承
    -1.32
    MemoryWarning
    -1.30
     минуту
    -1.30
     doesn
    -1.28
    ሖ
    -1.27
    %")
    -1.26
    POSITIVE LOGITS
     cuidadosamente
    1.35
     dessutom
    1.27
     sonunda
    1.21
     öfter
    1.18
    createdDate
    1.17
    jaket
    1.16
     小学校
    1.13
     koszt
    1.13
     evangé
    1.13
     همچنین
    1.12
    Activations Density 0.040%

    No Known Activations