© 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. 117779
    Prev
    Next
    INDEX
    Explanations

    quotation marks indicating a quote

    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
     !!!!!
    -0.06
     இவ்வாறு
    -0.06
     !!!!
    -0.06
    ــ
    -0.06
     classic
    -0.06
     ........
    -0.06
     others
    -0.06
    !!!!
    -0.06
     Victorian
    -0.06
     !!
    -0.05
    POSITIVE LOGITS
     intelekt
    0.07
     allegedly
    0.06
    ระดับ
    0.06
    使其
    0.06
     stably
    0.06
     показателей
    0.06
    较高的
    0.06
     следующих
    0.06
    それを
    0.06
    其中
    0.06
    Activations Density 0.001%

    No Known Activations