© 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. 67774
    Prev
    Next
    INDEX
    Explanations

    a followed by adjective

    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
    ’
    -1.38
    が
    -1.33
     a
    -1.32
     复古
    -1.30
     kompon
    -1.26
    は
    -1.25
    に
    -1.24
    慙
    -1.20
     kopling
    -1.16
    是
    -1.16
    POSITIVE LOGITS
    感じが
    1.20
    ナメント
    1.18
     конструкция
    1.16
    c
    1.12
    assade
    1.10
    Примі
    1.10
    什么样的
    1.10
    為に
    1.09
     construite
    1.09
    卡通
    1.07
    Activations Density 0.051%

    No Known Activations