© 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. 67537
    Prev
    Next
    INDEX
    Explanations

    IEEE 802.15.4, inline void

    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
     and
    -1.63
     %).
    -1.52
    🤨
    -1.51
    ！”
    -1.46
    !!</
    -1.41
     Coupé
    -1.39
     stiefel
    -1.38
    enses
    -1.38
     ?”
    -1.38
    !!!”
    -1.36
    POSITIVE LOGITS
    alatan
    1.54
     σήμερα
    1.41
    変わらず
    1.41
     Frühstück
    1.38
     dzisiaj
    1.37
    魠
    1.36
    買
    1.34
     sekarang
    1.34
    {
    1.34
    They
    1.33
    Activations Density 0.001%

    No Known Activations