© 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. 129325
    Prev
    Next
    INDEX
    Explanations

    not required

    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
     بسرعة
    -0.06
     enz
    -0.06
    лению
    -0.06
     جمال
    -0.06
     agh
    -0.06
    abab
    -0.06
     또
    -0.06
     complementary
    -0.06
     aceler
    -0.06
    関連
    -0.06
    POSITIVE LOGITS
     সকল
    0.07
    Consult
    0.06
     must
    0.06
     waitUntil
    0.06
    및
    0.06
     هیچ
    0.06
    Depending
    0.06
     চাপ
    0.06
     চাষ
    0.06
     جميع
    0.06
    Activations Density 0.005%

    No Known Activations