© 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. 39613
    Prev
    Next
    INDEX
    Explanations

    usually don't write or do

    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
    ولو
    -0.91
    keteers
    -0.90
    cae
    -0.89
    Descriere
    -0.89
     dieťa
    -0.87
     emblematic
    -0.85
     welkom
    -0.85
     illuminate
    -0.84
    维生素
    -0.82
    Knows
    -0.82
    POSITIVE LOGITS
     but
    1.21
    Usually
    1.05
     usually
    1.05
     Usually
    1.01
     this
    1.01
     such
    1.00
     але
    0.99
    歳の
    0.99
     EVER
    0.98
     обычно
    0.93
    Activations Density 0.020%

    No Known Activations