© 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. 74903
    Prev
    Next
    INDEX
    Explanations

    delete and remove

    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
    dijual
    -1.20
    Liên
    -1.12
     pól
    -1.11
     dekol
    -1.10
    sepatu
    -1.08
    damen
    -1.07
     nowy
    -1.06
    |$.
    -1.05
    spodnie
    -1.05
     nieuwe
    -1.05
    POSITIVE LOGITS
     if
    1.34
     remove
    1.03
     while
    0.94
     gradually
    0.94
     to
    0.94
     has
    0.93
     until
    0.93
     on
    0.91
     is
    0.90
    try
    0.90
    Activations Density 0.002%

    No Known Activations