© 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. 467
    Prev
    Next
    INDEX
    Explanations

    flipflop 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_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
     IMEI
    -0.80
    tigkeit
    -0.79
    IONS
    -0.77
     радиа
    -0.74
     stumped
    -0.73
    lanie
    -0.72
    ляют
    -0.71
     Tarif
    -0.71
    后台
    -0.71
     القرن
    -0.71
    POSITIVE LOGITS
     flip
    1.74
     Flip
    1.46
    Flip
    1.28
    flip
    1.20
     FF
    1.13
     flips
    0.94
     Storage
    0.93
     holding
    0.93
     flipped
    0.91
     storage
    0.89
    Activations Density 0.057%

    No Known Activations