© 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. 120453
    Prev
    Next
    INDEX
    Explanations

    code markers

    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
    それぞれ
    -0.07
     گذا
    -0.06
     detailed
    -0.06
     each
    -0.06
     각각
    -0.06
    分別
    -0.06
     respectively
    -0.06
    или
    -0.06
     соответственно
    -0.06
     रुका
    -0.06
    POSITIVE LOGITS
    だけ
    0.07
    Fuck
    0.07
     only
    0.07
     fucking
    0.07
     ainult
    0.07
     tylko
    0.07
     fuck
    0.07
     früh
    0.06
     একটা
    0.06
     kunnen
    0.06
    Activations Density 0.004%

    No Known Activations