© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 128504
    Prev
    Next
    INDEX
    Explanations

    copyright and software licenses

    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
     необходи
    -0.08
    ことができます
    -0.07
     prepare
    -0.06
     تحتاج
    -0.06
    することができます
    -0.06
     دیگر
    -0.06
     അവളുടെ
    -0.06
     ہتھی
    -0.06
    的作用
    -0.06
    irá
    -0.06
    POSITIVE LOGITS
    新
    0.06
     increase
    0.06
    Sense
    0.06
    sense
    0.06
     An
    0.06
     for
    0.05
     menyatakan
    0.05
    后
    0.05
     jasno
    0.05
     betreff
    0.05
    Activations Density 0.003%

    No Known Activations