© 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. 120092
    Prev
    Next
    INDEX
    Explanations

    after website link or header

    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
     fatalities
    -0.06
     daño
    -0.06
     deftly
    -0.06
     производителя
    -0.06
     safety
    -0.06
     associates
    -0.06
     antagonists
    -0.06
     curios
    -0.06
     aktuell
    -0.06
     celulares
    -0.06
    POSITIVE LOGITS
     ability
    0.06
     種
    0.06
    تم
    0.06
     support
    0.06
    成功
    0.06
     würde
    0.06
    eleri
    0.06
    与
    0.05
    portion
    0.05
     mode
    0.05
    Activations Density 0.001%

    No Known Activations