© 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. 119336
    Prev
    Next
    INDEX
    Explanations

    mathematical labels and citations

    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
    jár
    -0.06
    ősz
    -0.06
    ixar
    -0.05
    айл
    -0.05
     melihat
    -0.05
     terdiri
    -0.05
     आपला
    -0.05
     यूनिवर्सिटी
    -0.05
     jusqu
    -0.05
    ythe
    -0.05
    POSITIVE LOGITS
     während
    0.07
     \,,
    0.06
     alcuna
    0.06
     kDa
    0.06
     אני
    0.06
     জানুয়ারি
    0.06
    新た
    0.06
     during
    0.06
     galore
    0.06
     durante
    0.06
    Activations Density 0.001%

    No Known Activations