© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118100
    Prev
    Next
    INDEX
    Explanations

    scores after to

    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
     оттен
    -0.07
    以及
    -0.07
     undertake
    -0.07
     समक्ष
    -0.07
     undertaking
    -0.07
     mnog
    -0.06
     undertaken
    -0.06
     austenitic
    -0.06
    においても
    -0.06
     angene
    -0.06
    POSITIVE LOGITS
    的
    0.07
    類的
    0.06
     is
    0.06
    ्यांना
    0.06
     at
    0.06
    ♝
    0.05
     las
    0.05
    今年
    0.05
    ks
    0.05
     осталось
    0.05
    Activations Density 0.002%

    No Known Activations