© 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. 120258
    Prev
    Next
    INDEX
    Explanations

    Wilson Lowry

    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
     sizeable
    -0.06
     oni
    -0.06
    Grund
    -0.06
    affected
    -0.06
     their
    -0.06
     slowly
    -0.06
     only
    -0.06
     développement
    -0.06
     não
    -0.06
    стым
    -0.06
    POSITIVE LOGITS
     as
    0.07
     another
    0.07
     такой
    0.07
     ANOTHER
    0.07
    while
    0.07
    Another
    0.07
     auffi
    0.07
     Another
    0.06
     futur
    0.06
     години
    0.06
    Activations Density 0.001%

    No Known Activations