© 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. 84959
    Prev
    Next
    INDEX
    Explanations

    how many or how much

    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
     that
    -1.79
     Сейчас
    -1.71
    寕
    -1.66
    y
    -1.64
     что
    -1.63
     Что
    -1.63
     手順
    -1.61
     somewhat
    -1.59
     매우
    -1.59
    縢
    -1.55
    POSITIVE LOGITS
    出た
    1.70
     his
    1.66
     which
    1.57
     welke
    1.51
     has
    1.51
    <th>
    1.46
    <bos>
    1.43
     bombilla
    1.41
    ถ้า
    1.41
    ),
    1.39
    Activations Density 0.063%

    No Known Activations