© 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. 98624
    Prev
    Next
    INDEX
    Explanations

    comparison operators and match

    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
     brilho
    -0.98
     cualquier
    -0.96
     câmbio
    -0.89
     Allows
    -0.88
     compromisso
    -0.85
    isal
    -0.85
    carlos
    -0.85
     laranja
    -0.85
     persu
    -0.85
     가능
    -0.84
    POSITIVE LOGITS
     what
    1.16
     from
    1.12
     our
    1.03
    Lycka
    0.94
    expected
    0.91
    SLA
    0.89
     consequently
    0.89
    AXI
    0.88
    ształ
    0.87
     expected
    0.86
    Activations Density 0.009%

    No Known Activations