© 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. 117069
    Prev
    Next
    INDEX
    Explanations

    notifications and offers

    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
     깜
    -0.06
    metic
    -0.05
     زن
    -0.05
    内容は
    -0.05
    ixes
    -0.05
    ängt
    -0.05
    還是
    -0.05
    なんか
    -0.05
    员工
    -0.05
     earlier
    -0.05
    POSITIVE LOGITS
     innych
    0.07
     andere
    0.07
     exquisite
    0.07
     necessities
    0.07
     other
    0.07
     lainnya
    0.06
     необходимости
    0.06
     Spectacular
    0.06
     World
    0.06
     Faced
    0.06
    Activations Density 0.002%

    No Known Activations