© 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. 110980
    Prev
    Next
    INDEX
    Explanations

    titles of organizations and places

    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
     leur
    -1.41
     ihrer
    -1.34
     they
    -1.33
    。
    -1.33
     its
    -1.32
    tocks
    -1.29
    vereign
    -1.28
    because
    -1.23
     â
    -1.19
    禤
    -1.19
    POSITIVE LOGITS
     of
    1.38
     and
    1.16
    wanan
    1.13
    ,
    1.13
     そう
    1.13
    ことになる
    1.12
     uruguay
    1.12
    わけで
    1.07
     quelquefois
    1.05
    ługość
    1.05
    Activations Density 0.219%

    No Known Activations