© 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. 130166
    Prev
    Next
    INDEX
    Explanations

    Q:

    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
    另一个
    -0.09
     друго
    -0.08
    另一
    -0.08
    另一种
    -0.07
     ANOTHER
    -0.07
     altro
    -0.07
     başka
    -0.06
    another
    -0.06
     másik
    -0.06
    ➔
    -0.06
    POSITIVE LOGITS
     চেষ্টা
    0.06
     moja
    0.06
    ml
    0.06
    knit
    0.06
    बॉल
    0.06
    management
    0.05
     أقل
    0.05
     নিয়ত
    0.05
     পায়ে
    0.05
    Members
    0.05
    Activations Density 0.001%

    No Known Activations