© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43201
    Prev
    Next
    INDEX
    Explanations

    alternative or replacement

    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
    museo
    -1.63
     kurie
    -1.62
    颏
    -1.61
    genodigd
    -1.60
     eriş
    -1.59
    Crispy
    -1.59
    忐
    -1.55
    謌
    -1.52
    くっ
    -1.52
     satış
    -1.52
    POSITIVE LOGITS
     Several
    1.84
     than
    1.80
    傳統
    1.79
    .”
    1.73
     Some
    1.73
     gave
    1.70
    。
    1.61
    罢了
    1.60
    充滿
    1.59
     took
    1.53
    Activations Density 0.013%

    No Known Activations