© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 110735
    Prev
    Next
    INDEX
    Explanations

    tos followed by ca or uf

    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
    錀
    -2.73
    up
    -2.73
     bandung
    -2.70
    所说的
    -2.66
    巨大的
    -2.63
     continúas
    -2.63
     моя
    -2.48
     及
    -2.47
     gmbh
    -2.45
     بنات
    -2.45
    POSITIVE LOGITS
    tos
    2.75
     様子
    2.63
    翃
    2.53
    轳
    2.52
    在我
    2.50
     Vereinigten
    2.39
    𖣔
    2.38
    ↵↵
    2.36
     Füßen
    2.34
    皲
    2.33
    Activations Density 0.004%

    No Known Activations