© 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. 57657
    Prev
    Next
    INDEX
    Explanations

    Rally Rest, talks, Australia, Joins

    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
     \
    -3.28
     You
    -2.89
     YOU
    -2.66
     However
    -2.64
    </em>
    -2.55
     หรือ
    -2.50
    嶮
    -2.48
     Luckily
    -2.47
     \&
    -2.39
     Однако
    -2.36
    POSITIVE LOGITS
    isations
    2.39
     blau
    2.27
    镔
    2.25
    _
    2.17
     fechar
    2.17
    牁
    2.13
    ——————
    2.13
    ſhip
    2.11
    茕
    2.11
     gekomen
    2.09
    Activations Density 0.005%

    No Known Activations