© 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. 130514
    Prev
    Next
    INDEX
    Explanations

    DIY, self, purchase, own

    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
     arbeitet
    -0.07
     speriment
    -0.06
     pracuje
    -0.06
     عالية
    -0.06
     creations
    -0.06
     পেট
    -0.06
     expanding
    -0.06
     गेले
    -0.06
     vừa
    -0.06
     निरंतर
    -0.06
    POSITIVE LOGITS
     self
    0.08
     DIY
    0.08
    purch
    0.07
    DIY
    0.07
     Self
    0.07
    Self
    0.07
    购买
    0.07
     কিন
    0.07
    purchase
    0.07
     comprar
    0.07
    Activations Density 0.046%

    No Known Activations