© 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. 129319
    Prev
    Next
    INDEX
    Explanations

    missed point or mistake

    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
     drei
    -0.07
     तीन
    -0.06
     sechs
    -0.06
     fünf
    -0.06
     தங்கள்
    -0.06
    Fantastic
    -0.06
     такой
    -0.06
     üç
    -0.06
     cinq
    -0.06
     توسط
    -0.06
    POSITIVE LOGITS
     previous
    0.06
     प्रीवियस
    0.06
     преж
    0.05
     cycles
    0.05
     eerder
    0.05
     provin
    0.05
     months
    0.05
     iterable
    0.05
    श्वर
    0.05
     enumerable
    0.05
    Activations Density 0.002%

    No Known Activations