© 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. 10-GEMMASCOPE-RES-131K
    7. 42292
    Prev
    Next
    INDEX
    Explanations

    extant studies

    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
    on
    -2.91
    今度
    -2.80
    five
    -2.80
    あぁ
    -2.70
    </b>
    -2.66
    是为了
    -2.66
    an
    -2.64
    えっ
    -2.59
    ほんとに
    -2.53
    久しぶり
    -2.52
    POSITIVE LOGITS
     If
    2.81
     When
    2.56
    各样的
    2.52
    RenderAtEndOf
    2.48
    你
    2.44
     UNIVERSIT
    2.44
    縂
    2.38
    )：
    2.36
     That
    2.30
    ValueGeneration
    2.30
    Activations Density 0.017%

    No Known Activations