© 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. 112138
    Prev
    Next
    INDEX
    Explanations

    Change order

    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
     zout
    -1.46
     اخیر
    -1.45
     today
    -1.44
     ${({
    -1.34
     sige
    -1.31
    -1.28
    DEZ
    -1.25
     jurk
    -1.20
     eene
    -1.20
     oogen
    -1.20
    POSITIVE LOGITS
     bús
    1.55
    tot
    1.41
     БО
    1.40
    だけでも
    1.40
    铙
    1.35
     церковь
    1.34
     hatta
    1.30
     TAMBÉM
    1.30
     affirme
    1.28
     yine
    1.27
    Activations Density 0.092%

    No Known Activations