© 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. 120013
    Prev
    Next
    INDEX
    Explanations

    email addresses ending in .com

    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
     plus
    -0.07
     preponder
    -0.07
     Service
    -0.06
    mostly
    -0.06
    运营
    -0.06
     দুইজন
    -0.06
     beserta
    -0.06
     Function
    -0.06
     بالإضافة
    -0.06
     nor
    -0.06
    POSITIVE LOGITS
     itaque
    0.07
     이제
    0.07
     나온
    0.06
     निगाह
    0.06
     kinds
    0.06
     inductively
    0.06
     fotografia
    0.06
    應用
    0.06
    ogado
    0.06
     equação
    0.06
    Activations Density 0.001%

    No Known Activations