© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128775
    Prev
    Next
    INDEX
    Explanations

    intense negative experiences

    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_22/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
    аа
    -1.28
     expérimentés
    -1.27
     then
    -1.27
    alties
    -1.26
    интере
    -1.26
     difficiles
    -1.24
     composés
    -1.23
    还不错
    -1.23
     émotions
    -1.21
    Publié
    -1.21
    POSITIVE LOGITS
     and
    1.41
     lutego
    1.38
     października
    1.33
     kathol
    1.32
    昀
    1.28
     stycznia
    1.27
     mixture
    1.27
     Pfar
    1.23
     Endlich
    1.23
     ordf
    1.21
    Activations Density 0.036%

    No Known Activations