© 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. 116601
    Prev
    Next
    INDEX
    Explanations

    css and style files

    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
     그리고
    -0.07
    そして
    -0.06
     соответствующие
    -0.06
    ]<<"
    -0.06
     поддержка
    -0.06
     entsprechende
    -0.06
    presentableId
    -0.06
     images
    -0.06
    '].'
    -0.06
     ভ্রমণের
    -0.06
    POSITIVE LOGITS
    Lors
    0.06
     нашем
    0.06
    เวลา
    0.06
     equipped
    0.06
     integrado
    0.06
     werden
    0.06
     unserer
    0.06
    When
    0.06
    میں
    0.05
    വ്
    0.05
    Activations Density 0.010%

    No Known Activations