© 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. 118080
    Prev
    Next
    INDEX
    Explanations

    start of something

    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
     envisions
    -0.07
     presentato
    -0.07
     future
    -0.06
     אל
    -0.06
     fulfills
    -0.06
     fulfils
    -0.06
     toekomst
    -0.06
     vittime
    -0.06
    現状
    -0.06
     విషయంలో
    -0.06
    POSITIVE LOGITS
     防止
    0.08
    开始
    0.08
     ಆರಂಭ
    0.07
    rapid
    0.07
     본격
    0.07
    開始
    0.07
     empezar
    0.07
     empez
    0.07
     beginnen
    0.06
     empezó
    0.06
    Activations Density 0.010%

    No Known Activations