© 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. 21812
    Prev
    Next
    INDEX
    Explanations

    cup product, cup orientation, cup cake

    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
     —
    -3.42
    .
    -2.81
    
    -2.70
    鄜
    -2.69
    愎
    -2.66
     $
    -2.58
    但是在
    -2.50
    
    -2.45
    所以在
    -2.34
    öpfer
    -2.34
    POSITIVE LOGITS
    ’
    3.09
    </strong>
    2.81
    Ꮫ
    2.70
    驭
    2.63
     vestido
    2.58
     аккура
    2.55
     sentada
    2.52
    इटम
    2.47
    ‌هایی
    2.44
     сказала
    2.36
    Activations Density 0.010%

    No Known Activations