© 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. 117332
    Prev
    Next
    INDEX
    Explanations

    #hashtags in prompts

    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
    ../
    -0.06
     when
    -0.06
    :
    -0.06
    aspx
    -0.06
     Huan
    -0.06
    -
    -0.06
    ..
    -0.06
     ..
    -0.06
     resumen
    -0.06
    入手
    -0.06
    POSITIVE LOGITS
     आणि
    0.06
     gets
    0.06
     paltry
    0.06
     सप्ताह
    0.06
     और
    0.06
     prothorace
    0.06
     काँग्रेस
    0.06
     उनके
    0.06
    Month
    0.06
     Cultura
    0.06
    Activations Density 0.006%

    No Known Activations