© 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. 16180
    Prev
    Next
    INDEX
    Explanations

    celebrities and famous people

    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
     even
    -1.25
     this
    -1.23
     for
    -1.23
     sees
    -1.14
     system
    -1.13
     玄関
    -1.10
     sogar
    -1.09
     redan
    -1.07
     że
    -1.05
    胎
    -1.04
    POSITIVE LOGITS
     celebrity
    1.53
     celebrities
    1.39
     kontro
    1.27
     osoby
    1.20
     lutar
    1.18
     популяр
    1.17
     julk
    1.17
     SOCIAL
    1.17
    Entertainment
    1.16
     spektak
    1.16
    Activations Density 0.099%

    No Known Activations