© 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. 130868
    Prev
    Next
    INDEX
    Explanations

    describing state or quality

    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
    ンピース
    -1.58
    ⢌
    -1.54
     anhänger
    -1.50
     kwamba
    -1.48
     itself
    -1.48
     própri
    -1.48
    顚
    -1.45
    庒
    -1.43
     dificil
    -1.41
     basan
    -1.40
    POSITIVE LOGITS
     who
    2.58
     as
    1.87
     has
    1.80
     whom
    1.77
    ’
    1.48
     and
    1.45
     in
    1.41
     after
    1.36
     nacido
    1.31
     have
    1.28
    Activations Density 0.151%

    No Known Activations