© 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. 127491
    Prev
    Next
    INDEX
    Explanations

    read followed by description or content

    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
     hacían
    -1.62
     and
    -1.47
    シャレ
    -1.30
    alquiler
    -1.29
     новом
    -1.28
    Tekst
    -1.26
    Seni
    -1.26
    cámara
    -1.25
    τής
    -1.23
    んでいた
    -1.23
    POSITIVE LOGITS
     They
    1.56
     akár
    1.53
    </blockquote>
    1.46
    ll
    1.45
     スカート
    1.45
    </h3>
    1.43
    msgTypes
    1.41
    ’
    1.39
    СЯ
    1.38
    ginate
    1.38
    Activations Density 0.004%

    No Known Activations