© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130151
    Prev
    Next
    INDEX
    Explanations

    // Licensed to

    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
     particularly
    -0.07
     particolarmente
    -0.07
     exceedingly
    -0.07
     besonders
    -0.07
     sensibilité
    -0.06
     extraordinarily
    -0.06
    particularly
    -0.06
    fourth
    -0.06
     remarkably
    -0.06
              
    -0.06
    POSITIVE LOGITS
    সুর
    0.06
     lacks
    0.06
     ;)
    0.06
     لاحظ
    0.06
    δ
    0.06
    を見
    0.06
     দেয়
    0.06
     does
    0.06
     things
    0.06
     Leider
    0.06
    Activations Density 0.004%

    No Known Activations