© 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. 116805
    Prev
    Next
    INDEX
    Explanations

    platform, idea, extraordinary, management

    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
    그리고
    -0.07
    …..
    -0.06
     According
    -0.06
     देखिएगा
    -0.06
     rekla
    -0.06
     一个
    -0.06
     그리고
    -0.06
     Eine
    -0.06
     (...)
    -0.06
    いくつかの
    -0.06
    POSITIVE LOGITS
    <bos>
    0.06
     housed
    0.06
     Gente
    0.06
    Bạn
    0.06
     चौथा
    0.06
     फ्लाई
    0.06
    uie
    0.05
    dual
    0.05
     الرابعه
    0.05
    рган
    0.05
    Activations Density 0.042%

    No Known Activations