© 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. 117022
    Prev
    Next
    INDEX
    Explanations

    numbers referring to multiplicity

    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
     three
    -0.09
     two
    -0.08
     два
    -0.08
     trzech
    -0.08
     THREE
    -0.07
     additional
    -0.07
     enhanced
    -0.07
     multiple
    -0.07
     mehrere
    -0.07
     one
    -0.07
    POSITIVE LOGITS
    流行的
    0.06
     برخی
    0.06
     නමුත්
    0.06
     परन्तु
    0.06
    人
    0.06
    மார
    0.06
     certos
    0.06
     społec
    0.06
     certaines
    0.06
     دونك
    0.06
    Activations Density 0.013%

    No Known Activations