© 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. 85575
    Prev
    Next
    INDEX
    Explanations

    political titles and roles followed by context

    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
     inaweza
    -1.34
    äldrar
    -1.22
     rychle
    -1.22
    辚
    -1.12
     cimetière
    -1.09
     italianos
    -1.09
    solve
    -1.08
    薨
    -1.06
     signé
    -1.05
     amables
    -1.04
    POSITIVE LOGITS
     at
    1.63
     have
    1.37
     who
    1.23
     whom
    1.09
     selama
    1.08
     and
    1.08
     Niedersch
    1.04
     for
    1.03
    畏
    1.02
     my
    1.02
    Activations Density 0.037%

    No Known Activations