© 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. 60812
    Prev
    Next
    INDEX
    Explanations

    stern sternal sternberg

    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
    NaCl
    -0.78
     马
    -0.77
     Steen
    -0.75
    çe
    -0.74
     NCS
    -0.71
    طب
    -0.71
    ifik
    -0.70
    barkeit
    -0.68
     سوال
    -0.68
    tcp
    -0.68
    POSITIVE LOGITS
     Archivado
    0.77
     LIGHTS
    0.77
     xdrive
    0.75
     ネイビー
    0.74
    اعده
    0.73
    fres
    0.72
    wheeler
    0.72
    ሁ
    0.70
     REPRESENTATIVES
    0.70
     KEV
    0.70
    Activations Density 0.022%

    No Known Activations