© 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. 119428
    Prev
    Next
    INDEX
    Explanations

    referencing mechanisms

    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
     prób
    -0.06
     únicamente
    -0.06
     plataforma
    -0.06
    ThemeProvider
    -0.06
     바로
    -0.06
    友好
    -0.06
     portability
    -0.06
     فقط
    -0.06
     electric
    -0.06
    ۽
    -0.06
    POSITIVE LOGITS
     Referenced
    0.07
     REFER
    0.06
     referenced
    0.06
     referido
    0.06
    REFER
    0.06
     depends
    0.06
    を参照
    0.06
    Dit
    0.06
    (`${
    0.05
    による
    0.05
    Activations Density 0.087%

    No Known Activations