© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101
    Prev
    Next
    INDEX
    Explanations

    What is included

    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
    Ḧ
    -1.61
     Visita
    -1.56
    蕖
    -1.55
    ܔ
    -1.55
    IBLIO
    -1.52
     Græ
    -1.52
    NÉ
    -1.51
     violon
    -1.48
    coroutines
    -1.45
    撄
    -1.45
    POSITIVE LOGITS
     and
    1.77
     a
    1.77
     for
    1.64
    f
    1.52
    l
    1.42
     beserta
    1.38
    v
    1.38
    ad
    1.35
    </h1>
    1.34
    natured
    1.33
    Activations Density 0.025%

    No Known Activations