© 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. 69932
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or decimals

    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
    cljs
    -0.72
     samman
    -0.69
    研发
    -0.69
     låter
    -0.68
    butterfly
    -0.68
    Koh
    -0.68
    зможно
    -0.67
    žiu
    -0.67
    rías
    -0.66
     ə
    -0.66
    POSITIVE LOGITS
    lievo
    0.77
    worpen
    0.76
     naprawdę
    0.76
    atology
    0.75
     warunk
    0.74
    αι
    0.74
     skrzy
    0.73
     maggiore
    0.72
     نک
    0.71
    icace
    0.71
    Activations Density 0.069%

    No Known Activations