© 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. 76538
    Prev
    Next
    INDEX
    Explanations

    Function, rural, EC, camera, filter

    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
     while
    -0.82
     each
    -0.80
     całość
    -0.77
     everything
    -0.77
     verfolgt
    -0.75
     AssemblyCulture
    -0.73
    指向
    -0.71
     توانید
    -0.71
     場
    -0.71
     miei
    -0.71
    POSITIVE LOGITS
     presentación
    0.97
     révé
    0.95
     vẫn
    0.91
     természetes
    0.90
     jeszcze
    0.88
     perdón
    0.88
     ainda
    0.86
    lepší
    0.85
    lire
    0.84
     cemented
    0.83
    Activations Density 0.001%

    No Known Activations