© 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. 100804
    Prev
    Next
    INDEX
    Explanations

    Wisconsin

    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
    !’
    -2.33
    糴
    -2.28
     hacen
    -2.28
    ,’
    -2.27
     mehrere
    -2.22
     have
    -2.20
    一边
    -2.20
     نیز
    -2.19
     verschied
    -2.19
    ’,
    -2.19
    POSITIVE LOGITS
     has
    2.42
    ers
    2.41
     '
    2.28
    ходить
    2.25
    ``
    2.22
    2.19
     {
    2.19
    нак
    2.16
    ada
    2.08
    shafen
    2.08
    Activations Density 0.005%

    No Known Activations