© 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. 117408
    Prev
    Next
    INDEX
    Explanations

    Quebec, Ontario, Jay Z

    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
    шту
    -0.89
     mémor
    -0.79
     planche
    -0.76
     беже
    -0.75
    zapatos
    -0.74
     délib
    -0.74
     Gunnar
    -0.71
     Profitez
    -0.71
    something
    -0.71
    Montreal
    -0.71
    POSITIVE LOGITS
     Garza
    0.93
    iedz
    0.89
    recv
    0.79
     boc
    0.77
    джет
    0.75
    办
    0.75
    ppens
    0.74
    uminescence
    0.74
    製品
    0.73
    zzel
    0.73
    Activations Density 0.020%

    No Known Activations