© 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. 128770
    Prev
    Next
    INDEX
    Explanations

    both, and, also

    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
     birkaç
    -0.08
     câteva
    -0.07
     няколко
    -0.07
     mehrere
    -0.07
    arnia
    -0.06
     widgets
    -0.06
    rische
    -0.06
    いくつかの
    -0.06
     ćemo
    -0.06
     juba
    -0.06
    POSITIVE LOGITS
    基础上
    0.06
    ങ്ങളുടെ
    0.06
     উভয়
    0.06
     простых
    0.06
    جة
    0.05
     junt
    0.05
    both
    0.05
     ambas
    0.05
     तसेच
    0.05
    ienen
    0.05
    Activations Density 0.010%

    No Known Activations