© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99841
    Prev
    Next
    INDEX
    Explanations

    acronym, internet abbreviations

    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
     to
    -2.19
     and
    -1.84
    却被
    -1.57
     then
    -1.52
    wonderful
    -1.49
    baly
    -1.47
    なもの
    -1.44
    鞄
    -1.41
     insec
    -1.41
     nomine
    -1.41
    POSITIVE LOGITS
     or
    2.56
    Hogyan
    1.85
     that
    1.69
    Karakteristik
    1.68
     mengganggu
    1.67
     referirse
    1.65
     Unglück
    1.62
    Tentang
    1.61
    Usually
    1.59
     eikä
    1.59
    Activations Density 0.127%

    No Known Activations