© 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. 120010
    Prev
    Next
    INDEX
    Explanations

    UNITED STATES of AMERICA

    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
    がございます
    -0.07
     ebenso
    -0.06
     due
    -0.06
    评
    -0.06
     उष्ण
    -0.06
     recomendamos
    -0.06
     ונ
    -0.06
    されている
    -0.06
     estas
    -0.06
     tampoco
    -0.06
    POSITIVE LOGITS
     Ultimate
    0.06
    重庆
    0.06
     Worcester
    0.06
     అనేది
    0.06
     Wolverhampton
    0.06
     intra
    0.06
     goth
    0.06
     Andover
    0.06
     fanáticos
    0.06
     Doncaster
    0.06
    Activations Density 0.001%

    No Known Activations