© 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. 101671
    Prev
    Next
    INDEX
    Explanations

    parental figures

    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
     any
    -1.42
     Conditioner
    -1.32
     vuitton
    -1.28
     Thị
    -1.23
    комплект
    -1.23
     verbre
    -1.23
     które
    -1.20
    .
    -1.20
     ännu
    -1.20
    但这
    -1.19
    POSITIVE LOGITS
     and
    1.43
     "=
    1.35
    )="
    1.34
    𝑦
    1.34
    ]=>
    1.30
    们的
    1.29
     "../../../
    1.29
    arching
    1.28
    ゼット
    1.27
     affirme
    1.27
    Activations Density 0.030%

    No Known Activations