© 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. 10-GEMMASCOPE-RES-131K
    7. 66346
    Prev
    Next
    INDEX
    Explanations

    down synonyms and related phrases

    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
    U
    -2.64
    M
    -2.47
    C
    -2.36
    P
    -2.22
    ↵
    -2.16
    including
    -2.16
    R
    -2.14
    F
    -2.06
    D
    -2.06
    つづく
    -2.03
    POSITIVE LOGITS
     télévis
    2.59
    RenderAtEndOf
    2.33
    今年
    2.31
     Ketika
    2.31
    饜
    2.25
     Membuat
    2.22
    焿
    2.17
     Tetapi
    2.14
    謖
    2.14
     Memiliki
    2.13
    Activations Density 0.007%

    No Known Activations