© 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. 10-GEMMASCOPE-RES-131K
    7. 99527
    Prev
    Next
    INDEX
    Explanations

    flip-flop circuits

    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_10/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
    后退
    -1.52
    搧
    -1.48
    鼍
    -1.48
    ⎆
    -1.39
     która
    -1.38
    毉
    -1.37
     dokonce
    -1.37
    consola
    -1.36
    𝜋
    -1.36
    conut
    -1.35
    POSITIVE LOGITS
     his
    1.65
    with
    1.55
     with
    1.54
     will
    1.52
     would
    1.52
     all
    1.44
     on
    1.38
    いただいて
    1.36
     out
    1.31
    With
    1.28
    Activations Density 0.001%

    No Known Activations