© 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. 118471
    Prev
    Next
    INDEX
    Explanations

    corruption and its consequences

    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
     voluntarily
    -0.06
    सन
    -0.06
    自己
    -0.06
    voluntary
    -0.06
     obligado
    -0.06
     Austin
    -0.06
    思想
    -0.05
     changed
    -0.05
    后悔
    -0.05
     Barbados
    -0.05
    POSITIVE LOGITS
     위의
    0.07
     Tarifleri
    0.06
     रफ्तार
    0.06
     훨
    0.06
     verwendet
    0.06
     분명
    0.06
     पीएफआई
    0.06
     Protecting
    0.06
    有时
    0.06
     위에
    0.06
    Activations Density 0.010%

    No Known Activations