© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 82
    Prev
    Next
    INDEX
    Explanations

    recurring cycles and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ного
    1.13
    ную
    0.89
    ;
    0.87
    ا
    0.85
    ק
    0.84
    し
    0.82
    ի
    0.79
    yle
    0.76
    ление
    0.76
    ys
    0.75
    POSITIVE LOGITS
     Cycles
    1.04
    प
    1.00
     CYCLE
    0.98
    r
    0.96
     Irina
    0.96
    ج
    0.95
    CYCLE
    0.95
    Y
    0.93
     Ons
    0.90
     cycles
    0.89
    Activations Density 0.015%

    No Known Activations