© 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. 119949
    Prev
    Next
    INDEX
    Explanations

    right to

    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
    ｷ
    -1.71
    StoryboardSegue
    -1.65
     aborted
    -1.64
    圖片
    -1.63
     hilos
    -1.61
    衚
    -1.60
    jącym
    -1.60
    𝟎
    -1.58
     teneur
    -1.55
     plupart
    -1.52
    POSITIVE LOGITS
    ↵
    1.93
     to
    1.82
     RIGHT
    1.55
     senza
    1.52
    ↵↵
    1.49
     ravaged
    1.45
     вертика
    1.45
    乀
    1.45
     miliardi
    1.43
     of
    1.42
    Activations Density 0.026%

    No Known Activations