© 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. 39765
    Prev
    Next
    INDEX
    Explanations

    hence the name

    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
    -1.59
     mères
    -1.48
     things
    -1.43
     is
    -1.34
    はその
    -1.34
     doen
    -1.33
     sentiers
    -1.32
    ETHING
    -1.31
     it
    -1.30
    湏
    -1.30
    POSITIVE LOGITS
     on
    1.91
     new
    1.55
     in
    1.43
     for
    1.41
    liegende
    1.27
    𖡼
    1.27
     or
    1.27
     to
    1.26
    !=
    1.26
     Arquivado
    1.25
    Activations Density 0.031%

    No Known Activations