© 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. 107550
    Prev
    Next
    INDEX
    Explanations

    latest versions and advancements

    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
     тези
    -0.92
     tidligere
    -0.92
     pequeño
    -0.90
    choly
    -0.90
    してしまった
    -0.89
     Pompeo
    -0.89
     pequeña
    -0.86
    autre
    -0.84
     usarlo
    -0.84
    ってしまった
    -0.84
    POSITIVE LOGITS
     latest
    5.22
    最新
    4.19
    Latest
    4.03
    latest
    4.00
     newest
    3.81
     Latest
    3.53
    最新的
    3.45
    最新の
    3.19
     newer
    3.16
     LATEST
    3.14
    Activations Density 0.148%

    No Known Activations