© 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. 69473
    Prev
    Next
    INDEX
    Explanations

    credit and fellowships

    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
    </h3>
    -1.51
     pouvait
    -1.40
    ’
    -1.38
     mencegah
    -1.35
     solchen
    -1.35
    )।
    -1.35
     seguras
    -1.32
     about
    -1.30
     poate
    -1.29
     berusaha
    -1.27
    POSITIVE LOGITS
    趼
    1.91
     作り方
    1.46
    ܖ
    1.41
    ᯾
    1.38
     spagnolo
    1.34
     科技
    1.30
    змы
    1.29
     samme
    1.28
     OTHER
    1.27
     OTHERS
    1.27
    Activations Density 0.009%

    No Known Activations