© 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. 130865
    Prev
    Next
    INDEX
    Explanations

    diva / Divas / Il Divo

    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
    1
    -3.00
    閙
    -2.56
    .“
    -2.50
    .”.
    -2.30
     eigenen
    -2.25
    。）
    -2.25
     gewähr
    -2.20
    咈
    -2.19
    ")
    -2.11
    ,'
    -2.09
    POSITIVE LOGITS
    ⃙
    2.69
    ゆく
    2.08
    </h1>
    1.99
     konus
    1.94
     levens
    1.91
     vientos
    1.88
    嚒
    1.88
    ⦊
    1.88
    ◆◇
    1.87
     italien
    1.85
    Activations Density 0.002%

    No Known Activations