© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 105427
    Prev
    Next
    INDEX
    Explanations

    Japan and Japanese

    np_acts-logits-general · gemini-2.5-flash-lite

    Japanese haiku

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     facult
    0.45
     caribbean
    0.45
     verification
    0.43
     "-"
    0.43
     коля
    0.43
     rapp
    0.43
     assimilated
    0.42
    ≜
    0.42
     Colombian
    0.42
     verifying
    0.42
    POSITIVE LOGITS
     Japan
    1.38
     Japanese
    1.35
     Japón
    1.34
     Япо
    1.33
     япон
    1.32
     Jepang
    1.32
    Japan
    1.30
     जापान
    1.28
    Japanese
    1.27
     Giappone
    1.27
    Activations Density 0.146%

    No Known Activations