© 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. 128631
    Prev
    Next
    INDEX
    Explanations

    state of citation

    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
    voting
    -0.06
     spilling
    -0.06
     उपभो
    -0.06
     armed
    -0.06
     خوب
    -0.06
     Mustache
    -0.06
     أنّ
    -0.06
    Armed
    -0.06
     وجود
    -0.06
     esche
    -0.06
    POSITIVE LOGITS
     riguard
    0.07
     বয়
    0.06
     കൂട
    0.06
     thereby
    0.06
    jän
    0.06
     china
    0.06
    の
    0.06
     sehr
    0.06
    ゆう
    0.06
     prenot
    0.05
    Activations Density 0.002%

    No Known Activations