© 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. 128718
    Prev
    Next
    INDEX
    Explanations

    followed by names/dates/numbers

    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
    ৮
    -0.06
     mencari
    -0.06
     Danach
    -0.06
    或者是
    -0.06
     ۸
    -0.06
    ২০
    -0.06
     suchen
    -0.06
     accolade
    -0.06
    წი
    -0.06
    buscar
    -0.06
    POSITIVE LOGITS
     விருப்ப
    0.07
     Monday
    0.06
     Saturday
    0.06
     Friday
    0.06
     maneiras
    0.05
     लॉर्ड
    0.05
     buffering
    0.05
    seq
    0.05
    Friday
    0.05
     DIY
    0.05
    Activations Density 0.031%

    No Known Activations