© 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. 116665
    Prev
    Next
    INDEX
    Explanations

    official/unofficial designation

    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
     నిర్మాణ
    -0.07
     화면
    -0.07
     فیلم
    -0.06
     detectives
    -0.06
     영화
    -0.06
     경제
    -0.06
     secure
    -0.06
     verzek
    -0.06
     karena
    -0.06
    經濟
    -0.06
    POSITIVE LOGITS
    Roaming
    0.07
     official
    0.06
     Airbus
    0.06
     ufficial
    0.06
     unofficial
    0.06
     endorsed
    0.06
    lyde
    0.06
    痘
    0.06
     designated
    0.06
     usar
    0.06
    Activations Density 0.010%

    No Known Activations