© 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. 85082
    Prev
    Next
    INDEX
    Explanations

    OpenGL, CUDA, Q&A, code snippets

    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
    AutoresizingMask
    -2.14
    phère
    -1.91
    ⸫
    -1.90
     anderer
    -1.86
    ayaquil
    -1.84
    :"-"`
    -1.83
     we
    -1.83
     MessageBoxIcon
    -1.79
     добавить
    -1.78
     Перейти
    -1.73
    POSITIVE LOGITS
    (
    2.55
    I
    2.13
     '
    2.13
    :
    1.82
    ichtete
    1.65
    tedì
    1.65
    A
    1.63
    aż
    1.63
    رسد
    1.55
    -
    1.55
    Activations Density 0.004%

    No Known Activations