© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43527
    Prev
    Next
    INDEX
    Explanations

    questions asking about you

    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
    鉝
    -1.38
     vinil
    -1.34
    whenever
    -1.33
     mandat
    -1.31
     servent
    -1.29
     geolog
    -1.26
     prohi
    -1.25
     monstru
    -1.23
     intrig
    -1.23
     素描
    -1.22
    POSITIVE LOGITS
     your
    2.25
     or
    2.02
     you
    1.67
     with
    1.48
     или
    1.48
     yourself
    1.32
     start
    1.32
    撓
    1.30
     swoje
    1.29
         
    1.28
    Activations Density 0.085%

    No Known Activations