© 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. 58938
    Prev
    Next
    INDEX
    Explanations

    unfinished business and resource breakdown

    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
     PÅ
    -1.27
    咳咳
    -1.08
     FÜR
    -1.03
    🤬
    -1.01
     tien
    -0.96
     VOOR
    -0.94
     perpé
    -0.93
     uku
    -0.93
     pár
    -0.93
     cérami
    -0.93
    POSITIVE LOGITS
     you
    1.67
     those
    1.52
     what
    1.52
     if
    1.51
     even
    1.37
     how
    1.36
     when
    1.29
     why
    1.28
     so
    1.25
     sometimes
    1.21
    Activations Density 0.005%

    No Known Activations