© 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. 117908
    Prev
    Next
    INDEX
    Explanations

    lifting water, flooding, return

    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
     shale
    -0.06
     ಬೇಕ
    -0.06
     slate
    -0.06
     Carbide
    -0.06
    ceq
    -0.06
     tại
    -0.06
     cười
    -0.06
    slate
    -0.06
    ရေး
    -0.06
    checking
    -0.06
    POSITIVE LOGITS
    长期
    0.07
     return
    0.07
     long
    0.07
    長期
    0.06
     Return
    0.06
     Former
    0.06
    Return
    0.06
    每月
    0.06
     consume
    0.06
     photoelectric
    0.06
    Activations Density 0.010%

    No Known Activations