© 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. 128423
    Prev
    Next
    INDEX
    Explanations

    pre-acc or sclerosis

    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
     grueling
    -0.06
    nyk
    -0.06
     fertig
    -0.06
     मरीज
    -0.06
    modification
    -0.06
     arid
    -0.06
    했고
    -0.06
     মাঝারি
    -0.05
     ■
    -0.05
     standardised
    -0.05
    POSITIVE LOGITS
     you
    0.08
     are
    0.07
     is
    0.07
     OTHER
    0.07
     gives
    0.06
     все
    0.06
     embedding
    0.06
     YOU
    0.06
     kontek
    0.06
     ALL
    0.06
    Activations Density 0.011%

    No Known Activations