© 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. 118357
    Prev
    Next
    INDEX
    Explanations

    marine gastropod

    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
    である
    -0.06
     হয়েছেন
    -0.06
     immedi
    -0.06
     സിനിമ
    -0.06
     பாராட்ட
    -0.06
    raged
    -0.06
     headlight
    -0.06
     사용
    -0.06
    IntegerValue
    -0.06
     Hochschule
    -0.06
    POSITIVE LOGITS
     from
    0.08
     (
    0.07
    from
    0.06
    -(
    0.06
     choix
    0.06
     choice
    0.06
     choices
    0.06
     北欧
    0.06
     выбор
    0.06
    almost
    0.05
    Activations Density 0.001%

    No Known Activations