© 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. 119330
    Prev
    Next
    INDEX
    Explanations

    variable names and 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
    多くの
    -0.06
     necessary
    -0.06
     മനസ
    -0.06
     dozens
    -0.06
    ované
    -0.06
     different
    -0.06
    了他
    -0.06
     Sath
    -0.06
     fewer
    -0.06
    },(
    -0.06
    POSITIVE LOGITS
     by
    0.07
     முடி
    0.06
     পারি
    0.06
     when
    0.05
    टो
    0.05
     συν
    0.05
     Sold
    0.05
     firefighters
    0.05
     congrat
    0.05
     frit
    0.05
    Activations Density 0.005%

    No Known Activations