© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 117885
    Prev
    Next
    INDEX
    Explanations

    body shape

    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
     or
    -0.08
     myself
    -0.07
     सलाद
    -0.07
     if
    -0.07
     принад
    -0.07
    私の
    -0.06
    私が
    -0.06
     моих
    -0.06
     वेजिट
    -0.06
     моей
    -0.06
    POSITIVE LOGITS
     지난해
    0.06
     realizar
    0.06
     hacen
    0.06
     supposedly
    0.06
     reportedly
    0.06
     verdicts
    0.06
     functionalities
    0.06
     homeostasis
    0.05
     redefined
    0.05
     adap
    0.05
    Activations Density 0.001%

    No Known Activations