© 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. 129374
    Prev
    Next
    INDEX
    Explanations

    inflammatory muscle diseases

    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
    ject
    -0.06
     регули
    -0.06
     уз
    -0.06
     now
    -0.06
     ki
    -0.06
    !!!!!!
    -0.06
     устанавли
    -0.06
     spermatozoa
    -0.06
     abscess
    -0.06
    م
    -0.06
    POSITIVE LOGITS
    Expenses
    0.07
     NADH
    0.06
     REI
    0.06
     mileage
    0.06
    纷纷
    0.06
     aventure
    0.06
     vuelve
    0.06
    ⛏
    0.06
     alcohol
    0.06
    }^*
    0.06
    Activations Density 0.021%

    No Known Activations