© 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. 117872
    Prev
    Next
    INDEX
    Explanations

    former vs latter

    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
    なども
    -0.06
    かもしれませんが
    -0.05
     όμως
    -0.05
    ストラップ
    -0.05
    기와
    -0.05
    👈
    -0.05
     autoimmune
    -0.05
     untrue
    -0.05
    żs
    -0.05
    раздо
    -0.05
    POSITIVE LOGITS
     которое
    0.07
     includes
    0.07
     which
    0.07
    φέρον
    0.06
     Associations
    0.06
    Associations
    0.06
     THREE
    0.06
     které
    0.06
    gives
    0.06
     cannot
    0.06
    Activations Density 0.006%

    No Known Activations