© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117981
    Prev
    Next
    INDEX
    Explanations

    polyfill/replacement

    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
     với
    -0.07
     variety
    -0.07
    variety
    -0.06
     Oriental
    -0.06
    を表
    -0.06
     type
    -0.06
     veřej
    -0.06
     dengan
    -0.06
     použív
    -0.06
     foreseeable
    -0.06
    POSITIVE LOGITS
    графии
    0.06
     replacement
    0.06
    ზრ
    0.06
     забезпечення
    0.06
     प्रकाशित
    0.06
     replacements
    0.06
     surrogate
    0.05
     necessary
    0.05
     replic
    0.05
     substitutes
    0.05
    Activations Density 0.006%

    No Known Activations