© 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. 22-GEMMASCOPE-RES-131K
    7. 15636
    Prev
    Next
    INDEX
    Explanations

    ABSTRACT

    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_22/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
    жек
    -1.20
     recommande
    -1.11
     selam
    -1.09
    €”
    -1.09
     garantie
    -1.06
    дри
    -1.05
     envio
    -1.04
     Consiglio
    -1.03
     plana
    -1.02
     merak
    -1.02
    POSITIVE LOGITS
     pertanto
    1.02
     sostegno
    0.99
    Epilogue
    0.96
     ciascuno
    0.95
    Hehe
    0.95
     präsentieren
    0.95
     qualunque
    0.94
    ものを
    0.94
     consape
    0.93
     ognuno
    0.93
    Activations Density 0.001%

    No Known Activations