© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93319
    Prev
    Next
    INDEX
    Explanations

    previous official pages

    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
     never
    -0.84
     still
    -0.81
    —¡
    -0.76
    U
    -0.74
     Staffel
    -0.74
     Ut
    -0.74
    SessionFactory
    -0.74
    ik
    -0.74
     U
    -0.73
     Staaten
    -0.73
    POSITIVE LOGITS
     previous
    1.27
     предыду
    1.26
    previous
    1.23
     vorige
    1.21
     other
    1.08
     früheren
    1.05
     autre
    1.02
     دیگری
    0.99
    Previous
    0.97
     PREVIOUS
    0.96
    Activations Density 0.142%

    No Known Activations