© 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. 118188
    Prev
    Next
    INDEX
    Explanations

    zippered pouches

    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
     учетом
    -0.06
     avec
    -0.06
     fluidity
    -0.06
     versatility
    -0.06
     features
    -0.06
     Prosecutors
    -0.06
     improved
    -0.06
     with
    -0.06
     advantages
    -0.06
        
    -0.06
    POSITIVE LOGITS
     rất
    0.07
     very
    0.07
    很是
    0.07
     dość
    0.07
     fairly
    0.07
    或者是
    0.07
    非常
    0.07
     just
    0.07
     каждом
    0.07
     досить
    0.07
    Activations Density 0.001%

    No Known Activations