© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120059
    Prev
    Next
    INDEX
    Explanations

    treatment for cancer

    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
     can
    -0.07
     the
    -0.06
     progett
    -0.06
     velik
    -0.06
     examples
    -0.06
     models
    -0.06
     developments
    -0.06
    баров
    -0.06
    崙
    -0.06
    尝试
    -0.06
    POSITIVE LOGITS
     सीट
    0.06
    コントロール
    0.06
     meeste
    0.06
    োদিত
    0.06
     +'
    0.06
     who
    0.06
     dichos
    0.06
     Budd
    0.06
    unitary
    0.06
     uniform
    0.06
    Activations Density 0.025%

    No Known Activations