© 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. 70334
    Prev
    Next
    INDEX
    Explanations

    Ext.js code

    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
     otros
    -1.57
     være
    -1.38
     being
    -1.34
     müssen
    -1.29
    other
    -1.27
     outros
    -1.25
     οποίο
    -1.23
     other
    -1.22
     portuguesa
    -1.21
    р
    -1.20
    POSITIVE LOGITS
    ॑
    1.42
    大きさ
    1.27
     hjälper
    1.22
    異なります
    1.20
     тот
    1.20
    荩
    1.20
     höhere
    1.18
    ariate
    1.18
     you
    1.16
    ícula
    1.16
    Activations Density 0.019%

    No Known Activations