© 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. 129444
    Prev
    Next
    INDEX
    Explanations

    php, price, function, replace, constant

    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
     ALSO
    -0.07
    一些
    -0.07
     some
    -0.07
     också
    -0.07
     EVEN
    -0.06
     önüne
    -0.06
     także
    -0.06
    を用いる
    -0.06
    ACT
    -0.06
     véritable
    -0.06
    POSITIVE LOGITS
     takich
    0.07
     conformément
    0.07
     wollte
    0.06
     відповідно
    0.06
    詳しくは
    0.06
     zgodnie
    0.06
     respectively
    0.06
    অব
    0.06
     gemäß
    0.06
     allevi
    0.06
    Activations Density 0.014%

    No Known Activations