© 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. 119350
    Prev
    Next
    INDEX
    Explanations

    access for user

    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
     దీ
    -0.07
     constraint
    -0.06
     restraint
    -0.06
     শ্
    -0.06
     reclamation
    -0.06
     Floors
    -0.06
     owners
    -0.06
     Acquisitions
    -0.06
     প্লে
    -0.06
     empowering
    -0.05
    POSITIVE LOGITS
     if
    0.07
     ако
    0.06
     huv
    0.06
     sotto
    0.06
    USE
    0.06
    Team
    0.06
     если
    0.06
     wybor
    0.06
     मौत
    0.06
    应急
    0.06
    Activations Density 0.006%

    No Known Activations