© 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. 10-GEMMASCOPE-RES-131K
    7. 123605
    Prev
    Next
    INDEX
    Explanations

    choice, preference, and liking

    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_10/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
     vinci
    -1.43
     of
    -1.42
     istan
    -1.39
     nocturne
    -1.34
    ABULARY
    -1.34
     Kartu
    -1.34
    ......”
    -1.32
     Frankrijk
    -1.32
     Nieuws
    -1.31
     lagar
    -1.30
    POSITIVE LOGITS
     pudieran
    1.43
     You
    1.35
     mysterious
    1.34
     jednak
    1.32
     disminuir
    1.30
    になりますが
    1.30
     However
    1.30
     Also
    1.29
     pertenecen
    1.26
     most
    1.23
    Activations Density 0.025%

    No Known Activations