© 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. 908
    Prev
    Next
    INDEX
    Explanations

    bitter sweet, hollow, short-lived

    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
    </th>
    -1.41
     like
    -1.41
     eighty
    -1.21
    獗
    -1.21
     tons
    -1.21
     people
    -1.20
     other
    -1.20
    <i>
    -1.19
    </code>
    -1.17
     unusually
    -1.16
    POSITIVE LOGITS
     знал
    1.30
     soutě
    1.27
    بعض
    1.19
     místě
    1.19
     setiap
    1.19
    manned
    1.19
    ПРИ
    1.17
     losses
    1.17
     beiden
    1.16
    ֎
    1.16
    Activations Density 0.028%

    No Known Activations