© 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. 129384
    Prev
    Next
    INDEX
    Explanations

    institutional names and specific phrases

    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
     emplea
    -0.07
     بينما
    -0.07
     desperation
    -0.07
     KPSS
    -0.06
    '$
    -0.06
     小学
    -0.06
    பசு
    -0.06
     ске
    -0.06
    
    -0.06
     collège
    -0.06
    POSITIVE LOGITS
     benefactor
    0.06
    ajas
    0.06
     scl
    0.06
     सबकुछ
    0.06
     sast
    0.06
     cafeteria
    0.06
     Membership
    0.06
    隱
    0.06
     internally
    0.06
     Einrichtungen
    0.06
    Activations Density 0.007%

    No Known Activations