© 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. 105283
    Prev
    Next
    INDEX
    Explanations

    emerged as

    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
     these
    -1.88
     and
    -1.74
     with
    -1.70
     when
    -1.62
     those
    -1.60
     about
    -1.52
    ные
    -1.45
    ÑOS
    -1.41
     everything
    -1.41
     costs
    -1.40
    POSITIVE LOGITS
    </h2>
    1.59
     waren
    1.55
    .”
    1.48
     задач
    1.38
     szolg
    1.37
     sinnvoll
    1.36
     ANOTHER
    1.35
     hilfreich
    1.33
     vagyok
    1.31
     gustado
    1.31
    Activations Density 0.024%

    No Known Activations