© 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. 116957
    Prev
    Next
    INDEX
    Explanations

    htaccess rewrite rules

    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
     luxury
    -0.07
     will
    -0.07
     cook
    -0.06
     discussion
    -0.06
     unserer
    -0.06
     будут
    -0.06
     value
    -0.06
     controversy
    -0.06
     akan
    -0.06
     a
    -0.06
    POSITIVE LOGITS
    Helper
    0.06
    Aye
    0.06
     arrivé
    0.06
    iciado
    0.06
    entrant
    0.06
     близько
    0.06
    初
    0.06
    льны
    0.06
     arrangements
    0.06
    不是
    0.06
    Activations Density 0.009%

    No Known Activations