© 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. 118844
    Prev
    Next
    INDEX
    Explanations

    clinical experience

    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
    了一下
    -0.06
     obviamente
    -0.06
    起了
    -0.06
     tööt
    -0.05
     صارت
    -0.05
     übrigens
    -0.05
     একট
    -0.05
     advertise
    -0.05
     sentencing
    -0.05
     lighthouse
    -0.05
    POSITIVE LOGITS
     Italian
    0.06
    從
    0.06
     potent
    0.06
     लहान
    0.06
     inclusión
    0.06
     désir
    0.06
     નાના
    0.06
     छोटे
    0.06
     کوچک
    0.06
     small
    0.06
    Activations Density 0.001%

    No Known Activations