© 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. 130718
    Prev
    Next
    INDEX
    Explanations

    making sure that

    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
     utilizes
    -1.43
     utiliza
    -1.41
    <eos>
    -1.38
    ’,
    -1.33
     muertos
    -1.27
    ఎ
    -1.26
    шные
    -1.22
     commences
    -1.19
     yılında
    -1.19
     chooses
    -1.19
    POSITIVE LOGITS
    ley
    1.43
    nadequate
    1.41
    igth
    1.39
    裥
    1.38
    excellents
    1.38
    了嗎
    1.38
    nev
    1.36
    謂
    1.34
    l
    1.30
    siah
    1.30
    Activations Density 0.013%

    No Known Activations