© 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. 118713
    Prev
    Next
    INDEX
    Explanations

    host apparatus

    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
     kindred
    -0.06
     প্রদর্শন
    -0.06
     benzer
    -0.06
    已经
    -0.06
    最後に
    -0.06
    ಭವ
    -0.06
    cohort
    -0.05
     전략
    -0.05
     国内
    -0.05
     фер
    -0.05
    POSITIVE LOGITS
     primarily
    0.07
     shared
    0.06
    `:
    0.06
     Transfers
    0.06
     principalmente
    0.06
     mainly
    0.06
    primarily
    0.06
     ､
    0.06
     Mainly
    0.06
     communication
    0.06
    Activations Density 0.010%

    No Known Activations