© 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. 118983
    Prev
    Next
    INDEX
    Explanations

    closing punctuation in code

    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
     noteworthy
    -0.07
     But
    -0.06
     Extremely
    -0.06
     किंतु
    -0.06
     但
    -0.06
    규모
    -0.06
    Eventually
    -0.06
     drooping
    -0.06
     extremely
    -0.06
     severely
    -0.05
    POSITIVE LOGITS
    把
    0.07
    われた
    0.07
    扶
    0.07
    一款
    0.06
     konuda
    0.06
     percepción
    0.06
     cuál
    0.06
     cuáles
    0.06
     melihat
    0.06
     opción
    0.06
    Activations Density 0.001%

    No Known Activations