© 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. 79637
    Prev
    Next
    INDEX
    Explanations

    finding mathematical functions

    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
     because
    -0.96
    lo
    -0.90
     also
    -0.89
    يكب
    -0.87
    不高
    -0.86
     Maio
    -0.85
     unique
    -0.80
    0
    -0.77
     then
    -0.76
     ES
    -0.76
    POSITIVE LOGITS
     antigos
    1.04
    āci
    1.00
    他们在
    0.97
    receita
    0.95
    Evet
    0.94
    这样一个
    0.94
    guien
    0.93
    suporte
    0.93
     ladite
    0.92
     санкт
    0.92
    Activations Density 0.048%

    No Known Activations