© 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. 22-GEMMASCOPE-RES-131K
    7. 27219
    Prev
    Next
    INDEX
    Explanations

    cart followed by import

    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
     takže
    -1.04
    lacement
    -1.03
     etc
    -1.00
    他也
    -1.00
     кстати
    -0.99
     nyug
    -0.96
    HasBeenSet
    -0.96
    писок
    -0.94
    calips
    -0.93
    これらの
    -0.92
    POSITIVE LOGITS
     its
    1.28
     ekos
    1.06
     pandemia
    1.03
     OUTER
    1.01
    PlayStation
    1.01
     it
    0.99
     ikan
    0.98
    Sekarang
    0.97
     itself
    0.97
    pekte
    0.96
    Activations Density 0.028%

    No Known Activations