© 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. 10-GEMMASCOPE-RES-131K
    7. 57410
    Prev
    Next
    INDEX
    Explanations

    Bose-Einstein condensates and ultracold atoms

    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_10/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
     новое
    -1.56
    是一種
    -1.43
    s
    -1.34
    ङ
    -1.23
     recording
    -1.23
    est
    -1.20
     inneren
    -1.18
    ing
    -1.17
     guess
    -1.16
     $-$
    -1.16
    POSITIVE LOGITS
    Noti
    1.23
    Même
    1.23
    ҫ
    1.15
    ahhh
    1.13
    Mesmo
    1.13
    旨
    1.09
     ū
    1.08
    Награды
    1.08
    Depuis
    1.08
    ilustra
    1.08
    Activations Density 0.050%

    No Known Activations