© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117680
    Prev
    Next
    INDEX
    Explanations

    blog content and purpose

    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
     त्रुट
    -0.07
     otorg
    -0.06
     χωρίς
    -0.06
    鲷
    -0.06
     v
    -0.06
     відста
    -0.06
    뤽
    -0.06
     charitable
    -0.06
     bzw
    -0.06
     stalling
    -0.06
    POSITIVE LOGITS
     explicitly
    0.06
     next
    0.06
     summarise
    0.06
     SHOULD
    0.06
    period
    0.06
     Before
    0.06
     처음
    0.06
     USED
    0.06
    最初
    0.06
     следующий
    0.05
    Activations Density 0.011%

    No Known Activations