© 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. 117776
    Prev
    Next
    INDEX
    Explanations

    kills tumor cells viability

    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
     writing
    -0.06
     защиту
    -0.06
    am
    -0.06
    ป้องกัน
    -0.06
    ,
    -0.06
    it
    -0.06
    celebr
    -0.06
    global
    -0.06
     it
    -0.05
     code
    -0.05
    POSITIVE LOGITS
     একেবারেই
    0.08
     potpuno
    0.07
     побе
    0.07
    役割
    0.07
     শুধুমাত্র
    0.07
     majest
    0.07
    全是
    0.07
     zdecyd
    0.07
     mujeres
    0.06
     utilizzare
    0.06
    Activations Density 0.034%

    No Known Activations