© 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. 129726
    Prev
    Next
    INDEX
    Explanations

    when for specific situations

    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
     by
    -1.12
     it
    -1.05
    찼
    -1.02
    PREPAR
    -1.01
     diferite
    -0.98
    byes
    -0.97
     berbagai
    -0.95
     verschiedene
    -0.94
     pomocí
    -0.94
    OBJETIVOS
    -0.94
    POSITIVE LOGITS
     gdy
    1.31
     for
    1.29
     miesto
    1.20
     larger
    1.18
    ABUL
    1.14
     esimerkiksi
    1.13
     kated
    1.13
     smaller
    1.13
     όταν
    1.13
     amikor
    1.13
    Activations Density 0.046%

    No Known Activations