© 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. 22-GEMMASCOPE-RES-131K
    7. 28095
    Prev
    Next
    INDEX
    Explanations

    both occasions

    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_22/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
    玉ねぎ
    -0.79
     it
    -0.78
    ән
    -0.77
    áky
    -0.75
    upported
    -0.75
     quarters
    -0.71
    下に
    -0.71
     мысль
    -0.70
    setIcon
    -0.69
    ohistochemical
    -0.69
    POSITIVE LOGITS
     ambos
    1.71
     both
    1.69
    Both
    1.66
     beide
    1.64
    どちらも
    1.63
     оба
    1.59
     Beide
    1.56
     entrambi
    1.55
    ทั้ง
    1.49
     Both
    1.48
    Activations Density 0.081%

    No Known Activations