© 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. 117204
    Prev
    Next
    INDEX
    Explanations

    numbers, slashes, hyphens

    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
     malfunctioning
    -0.07
     estimation
    -0.07
     eigenfunctions
    -0.06
     disagreements
    -0.06
     যাবত
    -0.06
     bureaucratic
    -0.06
     automated
    -0.06
     behavi
    -0.06
     Despite
    -0.06
     wrecked
    -0.06
    POSITIVE LOGITS
     не
    0.07
     за
    0.07
     Не
    0.07
    を
    0.06
    ;
    0.06
     под
    0.06
     و
    0.06
     a
    0.06
     из
    0.06
     अकादमी
    0.06
    Activations Density 0.003%

    No Known Activations