© 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. 130456
    Prev
    Next
    INDEX
    Explanations

    errors following keywords

    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
    юсь
    -0.07
    🖊
    -0.06
     approximately
    -0.06
    授予
    -0.06
    Punj
    -0.06
     aproximadamente
    -0.06
     personalised
    -0.06
     နှစ်
    -0.06
    类似于
    -0.06
     אשר
    -0.06
    POSITIVE LOGITS
     आखिरी
    0.06
     हादसा
    0.06
     antiga
    0.06
     поперед
    0.06
    記錄
    0.06
     replaces
    0.06
     உற்ப
    0.06
    Ｍ
    0.06
    驗
    0.05
     पुराना
    0.05
    Activations Density 0.004%

    No Known Activations