© 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. 20366
    Prev
    Next
    INDEX
    Explanations

    losing something

    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
    郸
    -2.94
     Primarily
    -2.92
     usual
    -2.75
    section
    -2.72
     pitfalls
    -2.59
    数百
    -2.52
     This
    -2.47
    鲔
    -2.45
    ...?
    -2.45
    enfone
    -2.38
    POSITIVE LOGITS
    颀
    2.13
    缑
    2.06
    邙
    2.05
     machin
    2.03
     mélang
    2.02
    都没
    2.00
    инг
    1.97
     strto
    1.93
    kệ
    1.92
    的风
    1.91
    Activations Density 0.004%

    No Known Activations