© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65916
    Prev
    Next
    INDEX
    Explanations

    personal life and activities

    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
     that
    -2.22
     when
    -2.06
     during
    -2.02
     to
    -1.75
     where
    -1.67
     what
    -1.64
     throughout
    -1.58
     for
    -1.51
     then
    -1.51
     this
    -1.48
    POSITIVE LOGITS
    /><
    1.40
    才知道
    1.36
     نے
    1.32
     inconsciente
    1.28
     russe
    1.28
     Lightboxes
    1.25
     racc
    1.23
    cible
    1.23
     procédé
    1.23
    ☆☆☆☆
    1.22
    Activations Density 0.046%

    No Known Activations