© 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. 117603
    Prev
    Next
    INDEX
    Explanations

    and verb

    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
    ),
    -0.07
    들을
    -0.06
    不
    -0.06
    。
    -0.06
    더라고
    -0.06
    PUT
    -0.06
    各种
    -0.06
     injuring
    -0.06
    ほか
    -0.06
    抱着
    -0.05
    POSITIVE LOGITS
     भी
    0.07
    も
    0.07
     this
    0.07
     commonly
    0.07
     also
    0.06
    commonly
    0.06
     પણ
    0.06
     også
    0.06
     કહે
    0.06
    칵
    0.06
    Activations Density 0.034%

    No Known Activations