© 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. 71445
    Prev
    Next
    INDEX
    Explanations

    specific terms and their continuations

    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
     både
    -1.09
     soprattutto
    -1.01
    tacle
    -1.00
     найбіль
    -1.00
     traduit
    -0.98
     zj
    -0.96
    кладки
    -0.94
    Except
    -0.92
    ことはない
    -0.92
     compositeur
    -0.91
    POSITIVE LOGITS
     or
    1.83
     but
    1.79
     specific
    1.65
     specifically
    1.45
    specific
    1.42
     anymore
    1.27
    而是
    1.25
     אלא
    1.23
     particular
    1.21
     конкре
    1.21
    Activations Density 0.043%

    No Known Activations