© 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. 120522
    Prev
    Next
    INDEX
    Explanations

    proper nouns and sports terms

    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
    during
    -0.06
    electrolyte
    -0.06
    ,\
    -0.06
     directe
    -0.06
     weiteren
    -0.05
     રમ
    -0.05
    Elite
    -0.05
     Leads
    -0.05
    Financial
    -0.05
     بينما
    -0.05
    POSITIVE LOGITS
     suivi
    0.07
     முயற்சி
    0.07
     sullen
    0.07
     inhib
    0.06
     Polynesian
    0.06
     eigenes
    0.06
     consciente
    0.06
     davranış
    0.06
     Djokovic
    0.06
     datang
    0.06
    Activations Density 0.016%

    No Known Activations