© 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. 56100
    Prev
    Next
    INDEX
    Explanations

    loop, looping, loopback

    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
    𝙧
    -1.05
    榀
    -0.98
     небольшой
    -0.97
     provocando
    -0.96
    erschrank
    -0.95
    廡
    -0.94
    lyse
    -0.93
    וקה
    -0.93
    🕤
    -0.92
    Puedo
    -0.91
    POSITIVE LOGITS
    loop
    2.02
     Loop
    1.91
     loop
    1.64
    Loop
    1.55
     LOOP
    1.52
     loops
    1.51
     Loo
    1.28
     Loops
    1.24
     looping
    1.19
    LOOP
    1.08
    Activations Density 0.017%

    No Known Activations