© 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. 116342
    Prev
    Next
    INDEX
    Explanations

    20

    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
     आणि
    -0.09
     ಮತ್ತು
    -0.08
     και
    -0.08
     ਅਤੇ
    -0.08
     மற்றும்
    -0.07
     zawsze
    -0.07
     અને
    -0.07
     और
    -0.07
     complètement
    -0.07
    IDs
    -0.06
    POSITIVE LOGITS
    =
    0.07
     bâ
    0.06
     mediante
    0.06
    द्वारे
    0.06
    若
    0.06
    根据
    0.06
     melalui
    0.05
    による
    0.05
    臬
    0.05
     ул
    0.05
    Activations Density 0.038%

    No Known Activations