© 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. 118905
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and code structure

    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
     Zodiac
    -0.07
    historic
    -0.06
     kino
    -0.06
     pH
    -0.06
    further
    -0.06
     Shuffle
    -0.06
     Crazy
    -0.06
    bearers
    -0.06
     Each
    -0.06
    Crazy
    -0.06
    POSITIVE LOGITS
     výkon
    0.07
     विश्वास
    0.07
     במס
    0.06
     कामकाज
    0.06
     mengunjungi
    0.06
     trainings
    0.06
     informations
    0.06
     funzionamento
    0.06
     কালো
    0.06
    তীশ
    0.06
    Activations Density 0.034%

    No Known Activations