© 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. 19100
    Prev
    Next
    INDEX
    Explanations

    visual representation and intelligence

    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
    开来
    -1.80
    為了
    -1.74
    𝘁
    -1.58
    ”,
    -1.57
    ྂ
    -1.52
    ).
    -1.50
    ’,
    -1.46
     sabbia
    -1.46
     Aussehen
    -1.45
    ‘
    -1.45
    POSITIVE LOGITS
    鹩
    2.08
    </h3>
    1.84
     Visual
    1.73
    และ
    1.70
    visual
    1.65
     "'
    1.65
    "{\
    1.62
    🫃
    1.59
    Visual
    1.58
    臯
    1.52
    Activations Density 0.047%

    No Known Activations