© 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. 34-GEMMASCOPE-RES-131K
    7. 31325
    Prev
    Next
    INDEX
    Explanations

    want you to

    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
    aughey
    -0.98
    :\\
    -0.95
    我已经
    -0.94
     کجا
    -0.94
    Ketua
    -0.93
    "$_
    -0.93
     Gehalt
    -0.92
     thuyết
    -0.88
    être
    -0.88
    Belum
    -0.87
    POSITIVE LOGITS
     you
    2.50
     everyone
    2.02
     everybody
    1.41
    everyone
    1.31
     to
    1.22
    Everyone
    1.21
     thank
    1.16
    Thank
    1.15
     us
    1.11
     Everyone
    1.10
    Activations Density 0.024%

    No Known Activations