© 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. 29016
    Prev
    Next
    INDEX
    Explanations

    shark

    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
    ?”
    -3.17
    真的很
    -2.78
    ↵
    -2.73
     But
    -2.64
    の意味
    -2.52
    龵
    -2.50
    铙
    -2.47
    I
    -2.34
    ญี่ป
    -2.34
     eyebrow
    -2.34
    POSITIVE LOGITS
     hvem
    2.89
    ꙁ
    2.84
    不该
    2.72
     thier
    2.55
    ༵
    2.45
    有两
    2.45
     kran
    2.42
    麃
    2.41
     nabi
    2.41
     questionSearch
    2.41
    Activations Density 0.005%

    No Known Activations