© 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. 64989
    Prev
    Next
    INDEX
    Explanations

    types of statements

    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
     -
    -2.09
     The
    -1.84
    {
    -1.81
     startling
    -1.77
     VERY
    -1.74
    就跟
    -1.74
    了出来
    -1.67
     are
    -1.67
     alguns
    -1.66
     They
    -1.66
    POSITIVE LOGITS
    इटम
    2.28
    酲
    2.06
     difp
    1.98
     ftate
    1.88
    弹窗
    1.88
    🌼
    1.84
    <bos>
    1.80
    玏
    1.78
    Ⲉ
    1.77
    鲵
    1.76
    Activations Density 0.008%

    No Known Activations