© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117198
    Prev
    Next
    INDEX
    Explanations

    Japanese given name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     famed
    -0.07
     அதே
    -0.07
     unscathed
    -0.06
    通过
    -0.06
    বেক
    -0.06
     addicts
    -0.06
     allow
    -0.06
     bystanders
    -0.06
    Overall
    -0.06
     boasts
    -0.06
    POSITIVE LOGITS
     these
    0.06
     the
    0.06
     ৪০
    0.06
     serían
    0.05
     Production
    0.05
     Strategic
    0.05
     напа
    0.05
    るのは
    0.05
     행복
    0.05
     Initiation
    0.05
    Activations Density 0.001%

    No Known Activations