© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 130810
    Prev
    Next
    INDEX
    Explanations

    attempt, allege, required, testing

    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
    については
    -0.07
     as
    -0.06
    Concern
    -0.06
     most
    -0.06
    係
    -0.05
    ・・・。
    -0.05
    ²,
    -0.05
     Nesta
    -0.05
    silent
    -0.05
     হায়
    -0.05
    POSITIVE LOGITS
     badly
    0.07
    剛剛
    0.07
     difficoltà
    0.07
     caries
    0.06
     Childs
    0.06
     determinados
    0.06
     difficol
    0.06
     Introductory
    0.06
     condições
    0.06
     opravdu
    0.06
    Activations Density 0.001%

    No Known Activations