© 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. 129095
    Prev
    Next
    INDEX
    Explanations

    Greg Fidelman

    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
     sunny
    -0.07
     开
    -0.07
     ಹಲ
    -0.07
    🎡
    -0.06
    🎢
    -0.06
     huống
    -0.06
     sunshine
    -0.06
     fahren
    -0.06
    aruh
    -0.06
    ...).
    -0.06
    POSITIVE LOGITS
    স্থানীয়
    0.06
     gossip
    0.06
     ранее
    0.06
     warl
    0.06
     eliminate
    0.06
     précédemment
    0.06
    Transaction
    0.06
     rimu
    0.06
     incluso
    0.06
     remove
    0.06
    Activations Density 0.007%

    No Known Activations