© 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. 130602
    Prev
    Next
    INDEX
    Explanations

    import, Q, straight

    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
    私たちの
    -0.08
     مثال
    -0.08
    私たち
    -0.08
     вашего
    -0.07
     ваше
    -0.07
     あなた
    -0.07
     your
    -0.07
     ваши
    -0.07
     utilisée
    -0.07
     vaše
    -0.07
    POSITIVE LOGITS
     includes
    0.07
     consists
    0.06
     including
    0.06
     K
    0.06
     Kr
    0.06
     F
    0.06
    j
    0.05
     straight
    0.05
     Cf
    0.05
    Transform
    0.05
    Activations Density 0.002%

    No Known Activations