© 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. 129170
    Prev
    Next
    INDEX
    Explanations

    by (method/means)

    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
     numerose
    -0.08
    はこの
    -0.08
     भी
    -0.07
     zahlreichen
    -0.07
     banyak
    -0.07
     melalui
    -0.07
    숱
    -0.07
     случайно
    -0.06
     многочис
    -0.06
     வெற்றிய
    -0.06
    POSITIVE LOGITS
     for
    0.07
     để
    0.07
     to
    0.07
     against
    0.06
    ;
    0.06
    !!
    0.05
    skull
    0.05
     通販
    0.05
     de
    0.05
    roid
    0.05
    Activations Density 0.030%

    No Known Activations