© 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. 129980
    Prev
    Next
    INDEX
    Explanations

    Sixth nerve

    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
     ၁
    -0.07
     jalap
    -0.06
    看见
    -0.06
     yaklaşık
    -0.06
    ក្នុង
    -0.06
     amené
    -0.06
     પ્રથમ
    -0.06
     SIMPLE
    -0.06
    看到
    -0.06
    ிலிருந்து
    -0.06
    POSITIVE LOGITS
     உத
    0.06
    给她
    0.05
    必要的
    0.05
    掩
    0.05
    certs
    0.05
     gives
    0.05
    往往
    0.05
     года
    0.05
     &
    0.05
    чие
    0.05
    Activations Density 0.001%

    No Known Activations