© 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. 128459
    Prev
    Next
    INDEX
    Explanations

    shocks, front, topological, oxygen, shell, nucleotide

    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
     homosexuality
    -0.08
     prodigious
    -0.07
     sexual
    -0.07
     minuscule
    -0.07
     sizeable
    -0.06
    ğından
    -0.06
    複数
    -0.06
     syrup
    -0.06
     ostensibly
    -0.06
     مبنی
    -0.06
    POSITIVE LOGITS
     иссле
    0.07
    狩
    0.07
     chegada
    0.06
     contacted
    0.06
     frontera
    0.06
    皈
    0.06
    спеди
    0.06
    侘
    0.06
     arrival
    0.06
    觓
    0.06
    Activations Density 0.001%

    No Known Activations