© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82597
    Prev
    Next
    INDEX
    Explanations

    band company firm series

    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
    を
    -1.87
    と
    -1.84
    で
    -1.78
    が
    -1.65
    などを
    -1.41
    に
    -1.41
    这让
    -1.37
    逦
    -1.36
     Prefeitura
    -1.36
     discul
    -1.34
    POSITIVE LOGITS
     betyder
    1.35
    ところに
    1.35
    なんですね
    1.34
    だと思う
    1.30
    なのかな
    1.28
    なのでしょう
    1.26
    になってしまう
    1.26
    うえ
    1.26
     DÍA
    1.25
     mieste
    1.24
    Activations Density 0.317%

    No Known Activations