© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129666
    Prev
    Next
    INDEX
    Explanations

    keeping records or notes

    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
     interessant
    -0.06
     به‌عنوان
    -0.06
     इटावा
    -0.06
     interessante
    -0.06
     забруд
    -0.06
     cuentas
    -0.06
    Interesting
    -0.06
    为主
    -0.06
     interesting
    -0.06
     ""))
    -0.06
    POSITIVE LOGITS
     referendum
    0.06
    iyordu
    0.06
     TOO
    0.06
     குறித்து
    0.06
     последствия
    0.06
     mermaid
    0.06
     mence
    0.05
    findings
    0.05
     rifer
    0.05
     moment
    0.05
    Activations Density 0.011%

    No Known Activations