© 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. 3698
    Prev
    Next
    INDEX
    Explanations

    limit or quota

    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
    プーン
    -1.46
     strana
    -1.45
     nastro
    -1.38
     tempore
    -1.37
    裃
    -1.35
     all
    -1.34
     』
    -1.28
     頭
    -1.28
     tutur
    -1.27
    茲
    -1.26
    POSITIVE LOGITS
     amount
    1.73
     is
    1.54
    '
    1.52
     další
    1.47
     также
    1.42
    上限
    1.42
    worpen
    1.41
     jejich
    1.39
    臾
    1.38
    geoning
    1.34
    Activations Density 0.039%

    No Known Activations