© 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. 43
    Prev
    Next
    INDEX
    Explanations

    intervene or step in

    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
     you
    -1.47
     then
    -1.39
    '
    -1.38
     都
    -1.38
     accompanying
    -1.38
    не
    -1.37
    .
    -1.36
    ,
    -1.34
    /////////
    -1.34
     these
    -1.34
    POSITIVE LOGITS
    媜
    1.75
    と感じ
    1.67
    睹
    1.64
    IonicModule
    1.59
     Other
    1.55
     อย่าง
    1.53
     plong
    1.50
    s
    1.48
     откуда
    1.45
     distinguer
    1.45
    Activations Density 0.014%

    No Known Activations