© 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. 58982
    Prev
    Next
    INDEX
    Explanations

    latex image references

    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
     temperat
    -0.84
    çage
    -0.82
    Descripció
    -0.81
     GLUT
    -0.80
    鬣
    -0.78
    ジャマ
    -0.77
    ちら
    -0.76
     VOW
    -0.75
    Вид
    -0.75
     sprouts
    -0.73
    POSITIVE LOGITS
     şə
    0.83
     Planting
    0.79
    OuterAlt
    0.77
    幹
    0.77
    巖
    0.76
    planting
    0.76
     }}=\
    0.76
     deleteById
    0.75
    jeeling
    0.75
     Music
    0.74
    Activations Density 0.002%

    No Known Activations