© 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. 129419
    Prev
    Next
    INDEX
    Explanations

    URL prefixes and code/markup elements

    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
     noch
    -0.08
     nawet
    -0.07
     jeszcze
    -0.07
     surpre
    -0.07
     még
    -0.07
     confiança
    -0.07
     gemeinsam
    -0.07
     সক্র
    -0.07
     mistrust
    -0.07
     ainda
    -0.06
    POSITIVE LOGITS
    /
    0.06
    1
    0.06
    3
    0.06
    を備
    0.06
    तों
    0.06
    как
    0.05
     şeker
    0.05
    与
    0.05
    2
    0.05
    aur
    0.05
    Activations Density 0.001%

    No Known Activations