© 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. 129154
    Prev
    Next
    INDEX
    Explanations

    developmental stages

    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
     fórmula
    -0.07
    ശാസ്ത്ര
    -0.07
    早在
    -0.06
     such
    -0.06
    ೈನ
    -0.06
     otras
    -0.06
     eficaz
    -0.06
     महार
    -0.06
    Such
    -0.06
    stm
    -0.06
    POSITIVE LOGITS
     rowing
    0.06
     নতুন
    0.06
     neurologic
    0.06
     transitional
    0.06
     bridging
    0.06
     most
    0.06
     nuove
    0.06
     الانتق
    0.06
     neurolog
    0.06
     nieuwe
    0.06
    Activations Density 0.009%

    No Known Activations