© 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. 19684
    Prev
    Next
    INDEX
    Explanations

    DOT May

    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
    𓆏
    -1.51
     traverser
    -1.44
     ו
    -1.44
     varier
    -1.41
     spad
    -1.41
    ឵
    -1.41
    ⸰
    -1.39
    镲
    -1.38
    และ
    -1.38
     tricot
    -1.34
    POSITIVE LOGITS
    我们
    1.43
    Característica
    1.41
     Ancak
    1.40
     Membuat
    1.39
    Nå
    1.38
     Meningkatkan
    1.38
    Nosotros
    1.36
     You
    1.36
    为了
    1.35
    ของ
    1.34
    Activations Density 0.002%

    No Known Activations