© 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. 22-GEMMASCOPE-RES-131K
    7. 567
    Prev
    Next
    INDEX
    Explanations

    programming language 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
    j
    -1.20
    ৷
    -1.05
    t
    -1.05
     nivelul
    -1.04
    ことに
    -1.03
    还有
    -1.03
     พร
    -1.02
    N
    -1.02
    A
    -1.02
     cỡ
    -1.02
    POSITIVE LOGITS
     from
    1.45
    jelaskan
    1.37
     febru
    1.34
     koncert
    1.33
    معرفی
    1.30
    Makanan
    1.28
     profesora
    1.25
     komfort
    1.24
    焌
    1.23
    jangkau
    1.21
    Activations Density 0.010%

    No Known Activations