© 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. 127352
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with sqrt and ln

    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
    roughly
    -1.46
    rospy
    -1.44
     celles
    -1.41
    ViewChild
    -1.38
     allora
    -1.38
     тогда
    -1.34
    xii
    -1.34
    一些
    -1.31
     durante
    -1.30
     DIFFERENT
    -1.30
    POSITIVE LOGITS
     of
    1.54
    蒹
    1.34
    ～～～
    1.30
     chanteuse
    1.29
     its
    1.29
     abiye
    1.29
     today
    1.28
     imun
    1.27
     Septiembre
    1.27
     autorisation
    1.26
    Activations Density 0.046%

    No Known Activations