© 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. 35956
    Prev
    Next
    INDEX
    Explanations

    letter to the editor or paper

    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
    聍
    -2.56
    祘
    -2.38
    O
    -2.34
    情况下
    -2.33
     انگلیسی
    -2.27
     petites
    -2.27
    تیجه
    -2.27
     главный
    -2.27
    骈
    -2.27
    ulates
    -2.25
    POSITIVE LOGITS
     That
    3.39
     Then
    2.73
    </h1>
    2.38
    an
    2.33
     AND
    2.27
     podrá
    2.25
    面的
    2.20
    шего
    2.20
     Our
    2.17
     становится
    2.14
    Activations Density 0.013%

    No Known Activations