© 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. 119209
    Prev
    Next
    INDEX
    Explanations

    made from or prepared from

    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
     impossible
    -0.06
     mediante
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.05
     ему
    -0.05
     impossibile
    -0.05
    Hemos
    -0.05
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.05
    ↵↵↵↵↵↵↵↵↵↵↵
    -0.05
     بعنوان
    -0.05
     ис
    -0.05
    POSITIVE LOGITS
     aktuell
    0.07
     aktuelle
    0.07
     чего
    0.07
     aktuellen
    0.06
     जप
    0.06
     that
    0.06
    terrain
    0.06
    ⌈
    0.06
     хотя
    0.06
     นั่น
    0.06
    Activations Density 0.055%

    No Known Activations