© 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. 22-GEMMASCOPE-RES-131K
    7. 27013
    Prev
    Next
    INDEX
    Explanations

    Cast and film credits

    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
     who
    -1.33
     countries
    -1.22
     Server
    -1.16
     различни
    -1.13
     people
    -1.13
     Zugriff
    -1.09
     Nedir
    -1.09
     silnika
    -1.09
     Microbiol
    -1.08
     всеки
    -1.08
    POSITIVE LOGITS
     "]";
    1.18
    herent
    1.16
     BigNumberish
    1.09
    AFFIRMED
    1.08
     bouteilles
    1.05
    ೮
    1.05
    焐
    1.05
     дета
    1.05
    réhen
    1.04
     hesit
    1.03
    Activations Density 0.001%

    No Known Activations