© 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. 19036
    Prev
    Next
    INDEX
    Explanations

    Harvard scientists, coaches, invention

    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
     вижу
    -1.50
    *
    -1.48
    所有的
    -1.46
    y
    -1.38
    ities
    -1.31
     onerous
    -1.28
     schreiben
    -1.28
    All
    -1.27
    すべての
    -1.25
     impactful
    -1.24
    POSITIVE LOGITS
     will
    1.64
     you
    1.50
     can
    1.49
     Bakterien
    1.43
    瑛
    1.41
    ancang
    1.39
     considerazione
    1.36
     sentenza
    1.35
     better
    1.34
     varietà
    1.30
    Activations Density 0.000%

    No Known Activations