© 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. 117290
    Prev
    Next
    INDEX
    Explanations

    numeric answers to expressions

    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
     it
    -0.06
     profissional
    -0.06
    either
    -0.06
     Brian
    -0.06
     alku
    -0.06
    किला
    -0.05
     What
    -0.05
     Multi
    -0.05
     হারা
    -0.05
    ErrorCode
    -0.05
    POSITIVE LOGITS
    Despite
    0.07
    続ける
    0.07
     продолжа
    0.07
     unquestionably
    0.06
     unmist
    0.06
    繼續
    0.06
     hipster
    0.06
     majest
    0.06
     कैंडिडेट
    0.06
     인정
    0.06
    Activations Density 0.021%

    No Known Activations