© 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
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130687
    Prev
    Next
    INDEX
    Explanations

    cross-links or alkylating agents

    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
     కొంత
    -0.07
    함으로써
    -0.07
     some
    -0.06
     alcuni
    -0.06
    some
    -0.06
     nogle
    -0.06
    instead
    -0.06
     некоторых
    -0.06
    することで
    -0.06
     presumably
    -0.06
    POSITIVE LOGITS
     고민
    0.06
     deleter
    0.06
     personnal
    0.06
     ingress
    0.06
     endangering
    0.06
     asbestos
    0.06
    spapers
    0.06
    宿舍
    0.05
    clf
    0.05
    严重的
    0.05
    Activations Density 0.013%

    No Known Activations