© 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. 130954
    Prev
    Next
    INDEX
    Explanations

    usually, typically, common, likely

    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
    そこ
    -0.08
     or
    -0.06
     αργ
    -0.05
     औसत
    -0.05
     অবস্থ
    -0.05
     később
    -0.05
    ALWAYS
    -0.05
    孩
    -0.05
     ALWAYS
    -0.05
     eerste
    -0.05
    POSITIVE LOGITS
    㚐
    0.07
     podrían
    0.07
     suitable
    0.06
    可能會
    0.06
     potrebbe
    0.06
     pueden
    0.06
    可能会
    0.06
    需
    0.06
     speedily
    0.06
    ailable
    0.06
    Activations Density 0.012%

    No Known Activations