© 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. 116938
    Prev
    Next
    INDEX
    Explanations

    links and URLs

    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
    Pyrazole
    -0.06
    ]::-
    -0.06
     hev
    -0.06
     thì
    -0.06
     สำหรับ
    -0.06
     ceremon
    -0.06
    Associations
    -0.06
     nhưng
    -0.06
    本社
    -0.06
    空格
    -0.06
    POSITIVE LOGITS
    9
    0.07
     использование
    0.06
     தங்க
    0.06
    8
    0.06
     გამოყენ
    0.06
     エ
    0.06
     使用
    0.06
    াদান
    0.06
    बताया
    0.05
    only
    0.05
    Activations Density 0.001%

    No Known Activations