© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27420
    Prev
    Next
    INDEX
    Explanations

    convolutional layers

    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
    是否
    -1.30
    此事
    -1.23
     case
    -1.14
    包括
    -1.13
     Those
    -1.11
    惟
    -1.08
     and
    -1.04
     holds
    -1.03
     |
    -1.03
     it
    -1.03
    POSITIVE LOGITS
     primeros
    1.41
    ㉕
    1.30
     ร์
    1.23
    niť
    1.20
     鸡
    1.20
     firs
    1.19
    Mvh
    1.17
     vytvá
    1.16
     प्रोड
    1.16
    lardan
    1.15
    Activations Density 0.008%

    No Known Activations