© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71182
    Prev
    Next
    INDEX
    Explanations

    for loops

    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_22/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
    了一眼
    -0.88
    Makefile
    -0.83
     เว
    -0.83
     subnet
    -0.80
     hebben
    -0.80
     sonrası
    -0.79
    tipe
    -0.79
    clients
    -0.77
     marcó
    -0.77
    Chromosome
    -0.76
    POSITIVE LOGITS
     our
    1.16
     If
    1.01
     circunstancias
    0.98
    umpe
    0.93
     млрд
    0.90
     tries
    0.90
    Events
    0.85
    њу
    0.85
     events
    0.84
    เอา
    0.83
    Activations Density 0.003%

    No Known Activations