© 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. 117270
    Prev
    Next
    INDEX
    Explanations

    words starting with a punctuation

    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
     ENABLE
    -0.07
     आणि
    -0.06
     enabled
    -0.06
     ثم
    -0.06
     ۽
    -0.06
     ఏర్
    -0.06
     enables
    -0.06
     ഒരു
    -0.06
     Enabled
    -0.06
    然后在
    -0.06
    POSITIVE LOGITS
     for
    0.08
     zuvor
    0.07
     tedy
    0.06
     mož
    0.06
     similar
    0.06
     wnętr
    0.06
     살펴보도록
    0.06
    дж
    0.06
     "****
    0.06
    bauen
    0.06
    Activations Density 0.002%

    No Known Activations