© 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. 116512
    Prev
    Next
    INDEX
    Explanations

    next token after numbers

    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
     эти
    -0.06
     to
    -0.06
     ownership
    -0.05
     Shimano
    -0.05
     উভয়
    -0.05
     også
    -0.05
     गीता
    -0.05
    钥
    -0.05
    Ownership
    -0.05
     दोनों
    -0.05
    POSITIVE LOGITS
     là
    0.07
     và
    0.07
     sampai
    0.06
     denotes
    0.06
    łaszcza
    0.06
    刋
    0.06
    ́u
    0.06
     shrub
    0.06
     گیا۔
    0.06
     κάπο
    0.06
    Activations Density 0.001%

    No Known Activations