© 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. 116339
    Prev
    Next
    INDEX
    Explanations

    gene, equations, or variables

    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
    Durante
    -0.07
     ancestor
    -0.06
     продовжу
    -0.06
     davranış
    -0.06
    Під
    -0.06
    瘘
    -0.06
    inology
    -0.06
     CONTINUE
    -0.06
    adjustment
    -0.06
     नए
    -0.06
    POSITIVE LOGITS
     any
    0.06
     LGA
    0.06
     интересу
    0.05
     anyone
    0.05
    <0xEA>
    0.05
    ff
    0.05
    &\
    0.05
    Jets
    0.05
    cancel
    0.05
     இருந்தாலும்
    0.05
    Activations Density 0.050%

    No Known Activations