© 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. 26568
    Prev
    Next
    INDEX
    Explanations

    have fun

    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
     culturale
    -1.05
    ॉप
    -1.01
     аналоги
    -1.01
    ै
    -1.01
     ridiculously
    -1.01
     familiare
    -1.00
    pography
    -0.99
    vaila
    -0.98
    ë
    -0.96
    が無い
    -0.94
    POSITIVE LOGITS
     fun
    1.37
    อร่อย
    1.29
     शुर
    1.09
    大阪府
    1.09
    zdroj
    1.09
     classy
    1.05
     hyvä
    1.02
    umpulan
    1.02
     disfrut
    1.02
     enjoy
    1.02
    Activations Density 0.023%

    No Known Activations