© 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. 39842
    Prev
    Next
    INDEX
    Explanations

    Japanese government administration and infrastructure

    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
     if
    -1.23
    =""
    -1.02
     czerwca
    -1.02
    vereins
    -1.02
     stycznia
    -1.01
    radan
    -0.97
     recently
    -0.97
    getP
    -0.96
    ")))
    -0.95
     blev
    -0.93
    POSITIVE LOGITS
    ження
    1.41
     fortæ
    1.16
    áci
    1.13
     času
    1.06
    在了
    1.06
     proč
    1.05
    apparently
    1.05
    sterreich
    1.04
     kí
    1.03
     tæn
    1.03
    Activations Density 0.749%

    No Known Activations