© 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. 130331
    Prev
    Next
    INDEX
    Explanations

    bind attribute field name

    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
    click
    -0.06
    тивность
    -0.06
     immediately
    -0.05
     încep
    -0.05
     ため
    -0.05
    Ħ
    -0.05
     vê
    -0.05
     곧
    -0.05
    three
    -0.05
    すぐ
    -0.05
    POSITIVE LOGITS
    但
    0.07
     technisch
    0.07
     അല്ലെങ്കിൽ
    0.07
     technical
    0.06
     किंवा
    0.06
     teknik
    0.06
     तकनीकी
    0.06
     depends
    0.06
     ಅಥವಾ
    0.06
     அவசியம்
    0.06
    Activations Density 0.001%

    No Known Activations