© 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. 36335
    Prev
    Next
    INDEX
    Explanations

    execute, build, edit, recover, coverage

    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
    陷入
    -1.11
     latihan
    -1.08
    穿搭
    -1.06
    アンティーク
    -1.05
    さっそく
    -1.05
     pierde
    -1.00
    即便
    -0.98
    これからの
    -0.97
    即便是
    -0.96
     THEN
    -0.96
    POSITIVE LOGITS
     and
    1.17
    閙
    1.02
    kräfte
    1.00
    </em>
    0.98
     anderen
    0.97
     '_'
    0.96
    asjon
    0.95
    étaro
    0.95
    bidities
    0.92
    欽
    0.92
    Activations Density 0.003%

    No Known Activations