© 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. 120259
    Prev
    Next
    INDEX
    Explanations

    displaying information or results

    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
     beautiful
    -0.07
     horrendous
    -0.06
     zeer
    -0.06
    素晴らしい
    -0.06
    可通过
    -0.06
     وح
    -0.06
     disgusting
    -0.06
     receives
    -0.06
     abomin
    -0.06
     굉장히
    -0.06
    POSITIVE LOGITS
    Secure
    0.07
    诀
    0.06
     Secure
    0.06
     maxime
    0.06
     supporto
    0.06
     secur
    0.06
     guide
    0.06
    ?
    0.06
     volc
    0.06
    understanding
    0.06
    Activations Density 0.040%

    No Known Activations