© 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. 104001
    Prev
    Next
    INDEX
    Explanations

    actions leading to incidents

    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
     ugyan
    -1.23
    sitting
    -1.16
    着她
    -1.15
     zahrani
    -1.13
     suavemente
    -1.13
     traditionnelle
    -1.12
     {
    -1.12
     chcete
    -1.11
    ocl
    -1.11
     anglick
    -1.10
    POSITIVE LOGITS
     during
    1.68
     after
    1.36
     a
    1.35
     involving
    1.35
     Sebuah
    1.34
     was
    1.31
     überprü
    1.30
     on
    1.27
     sonno
    1.26
    :
    1.26
    Activations Density 0.209%

    No Known Activations