© 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. 11885
    Prev
    Next
    INDEX
    Explanations

    get started with

    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
     the
    -2.39
     integrada
    -1.94
     to
    -1.88
    面白かった
    -1.84
     fotográfica
    -1.81
    鋨
    -1.70
    盦
    -1.69
     流れ
    -1.65
    냑
    -1.64
    』(
    -1.63
    POSITIVE LOGITS
    釆
    1.73
     鐵
    1.73
    .,
    1.73
     戰
    1.69
     element
    1.68
     However
    1.68
     нам
    1.65
    ânico
    1.65
    </strong>
    1.64
     کنید
    1.64
    Activations Density 0.011%

    No Known Activations