© 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. 10-GEMMASCOPE-RES-131K
    7. 44734
    Prev
    Next
    INDEX
    Explanations

    c++ header includes

    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
     its
    -1.58
     about
    -1.55
     when
    -1.28
     it
    -1.28
     realizando
    -1.26
     ’
    -1.26
     before
    -1.23
     erschienen
    -1.20
     constantemente
    -1.16
     cambiando
    -1.15
    POSITIVE LOGITS
    Our
    1.74
    我們
    1.48
     énergé
    1.46
    私たち
    1.36
     preocupaciones
    1.33
    Although
    1.33
    Może
    1.33
     coû
    1.30
    Together
    1.30
    We
    1.29
    Activations Density 0.048%

    No Known Activations