© 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. 128827
    Prev
    Next
    INDEX
    Explanations

    horror movie and fiction

    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
     ক্রো
    -0.07
    such
    -0.06
    exposure
    -0.06
     SUCH
    -0.06
    cir
    -0.06
     Exposure
    -0.06
     কারন
    -0.06
    िरण
    -0.06
     обита
    -0.06
     Finch
    -0.06
    POSITIVE LOGITS
     toughest
    0.06
     adecuado
    0.06
     anew
    0.06
     elegant
    0.06
     veo
    0.06
    ಗಳು
    0.06
    quele
    0.06
     обеспечить
    0.06
     crisp
    0.06
    Elegant
    0.06
    Activations Density 0.009%

    No Known Activations