© 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. 34-GEMMASCOPE-RES-131K
    7. 33515
    Prev
    Next
    INDEX
    Explanations

    subject acted upon

    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_34/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
    已经
    -1.21
    และ
    -1.16
    ㈯
    -1.14
    旰
    -1.12
    であり
    -1.11
    而
    -1.07
     姫
    -1.06
     relâche
    -1.05
    はなく
    -1.05
    zwei
    -1.03
    POSITIVE LOGITS
     given
    1.60
     taken
    1.54
     sent
    1.38
     able
    1.27
     asked
    1.24
     kept
    1.16
     placed
    1.15
     brought
    1.14
     allowed
    1.14
     put
    1.12
    Activations Density 0.107%

    No Known Activations