© 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. 128624
    Prev
    Next
    INDEX
    Explanations

    starting punctuation or common tokens

    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
     tentang
    -0.07
    关于
    -0.07
     consisted
    -0.06
     về
    -0.06
    ร็จ
    -0.06
     recursively
    -0.06
     குறிப்பாக
    -0.06
     relative
    -0.06
    لوم
    -0.06
    เกี่ยวกับ
    -0.06
    POSITIVE LOGITS
     IELTS
    0.07
     benef
    0.07
     beneficia
    0.06
     diye
    0.06
     fak
    0.06
    이라는
    0.06
     শিল্পী
    0.06
    은
    0.06
    জগতের
    0.06
     it
    0.06
    Activations Density 0.001%

    No Known Activations