© 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. 351
    Prev
    Next
    INDEX
    Explanations

    references, draw, author, medal

    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
    lors
    -1.58
    nitř
    -1.41
     bijvoorbeeld
    -1.37
    дельник
    -1.37
     namelijk
    -1.36
     cubierta
    -1.34
     eerst
    -1.34
     تريد
    -1.34
     másik
    -1.33
    cetamol
    -1.30
    POSITIVE LOGITS
     (
    1.90
    8
    1.48
     to
    1.45
    are
    1.42
    so
    1.41
     даже
    1.41
    Considering
    1.40
    Before
    1.39
     =
    1.38
    There
    1.36
    Activations Density 0.043%

    No Known Activations