© 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. 33200
    Prev
    Next
    INDEX
    Explanations

    legal and governmental contexts

    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
     Mejor
    -1.23
    Ї
    -1.19
    нью
    -1.19
     musikk
    -1.17
    ridgeshire
    -1.17
     Kasım
    -1.16
    geç
    -1.14
    çok
    -1.13
    Karena
    -1.11
    otho
    -1.11
    POSITIVE LOGITS
    <h3>
    1.07
     surpresa
    1.06
     the
    1.04
     bestimmten
    1.04
     solchen
    1.03
    <h2>
    0.98
          
    0.97
    両方
    0.94
     Grüßen
    0.93
     disturbing
    0.93
    Activations Density 0.005%

    No Known Activations