© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104707
    Prev
    Next
    INDEX
    Explanations

    programming code keywords

    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_22/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
     recently
    -1.06
     lately
    -1.04
     terbaru
    -1.02
    最近は
    -1.01
     recent
    -1.01
    「
    -1.00
     ویتامین
    -0.97
     IconButton
    -0.96
    现有
    -0.96
    多次
    -0.94
    POSITIVE LOGITS
    ложений
    1.20
     systems
    1.19
     services
    1.18
     verkau
    1.16
    心臓
    1.16
    kanı
    1.15
     bestuur
    1.13
     everything
    1.13
    を抑
    1.12
    之事
    1.10
    Activations Density 0.084%

    No Known Activations