© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7750
    Prev
    Next
    INDEX
    Explanations

    context and loop

    np_acts-logits-general · gemini-2.5-flash-lite

    loops and iteration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    拔
    0.40
     Federation
    0.38
    พร
    0.38
    andam
    0.38
    肩
    0.35
     prosecuted
    0.34
    គ្ន
    0.34
    餞
    0.33
    ज्योति
    0.33
    ंबित
    0.33
    POSITIVE LOGITS
     loop
    4.84
    loop
    4.47
     loops
    4.47
     Loop
    4.41
    Loop
    4.31
     LOOP
    4.19
     Loops
    4.06
    loops
    3.98
    LOOP
    3.98
     looped
    3.94
    Activations Density 0.084%

    No Known Activations