© 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. 71481
    Prev
    Next
    INDEX
    Explanations

    numbers and ranges

    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
     different
    -1.22
     or
    -0.99
     signifikan
    -0.98
    áneamente
    -0.98
    Different
    -0.97
    每次
    -0.94
    šku
    -0.94
    stums
    -0.91
    بوط
    -0.90
    áním
    -0.88
    POSITIVE LOGITS
     desenho
    0.97
     veículo
    0.97
     acabamento
    0.96
     mlad
    0.93
     about
    0.92
     smrti
    0.91
    regalo
    0.91
     isomorphism
    0.89
    [
    0.89
     algorithm
    0.89
    Activations Density 0.011%

    No Known Activations