© 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. 130462
    Prev
    Next
    INDEX
    Explanations

    button click or search

    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
    self
    -0.06
    ilità
    -0.06
     వాటి
    -0.06
    EST
    -0.06
     FACILITIES
    -0.05
     アンティーク
    -0.05
     indicators
    -0.05
     തിരിച്ച
    -0.05
     hearty
    -0.05
    zta
    -0.05
    POSITIVE LOGITS
     ahora
    0.07
     که
    0.07
     now
    0.06
     that
    0.06
     που
    0.06
    的相关
    0.06
     eleven
    0.06
    வதை
    0.06
     entonces
    0.06
     auch
    0.06
    Activations Density 0.011%

    No Known Activations