© 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. 119160
    Prev
    Next
    INDEX
    Explanations

    already

    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
     clueless
    -0.06
     edgy
    -0.06
    笨
    -0.06
    ';"
    -0.06
     wonderfully
    -0.06
     seeming
    -0.06
     seem
    -0.05
     slippers
    -0.05
     veze
    -0.05
     moody
    -0.05
    POSITIVE LOGITS
     उर्व
    0.07
    永久
    0.07
     już
    0.07
    Already
    0.07
     Already
    0.07
     sofort
    0.06
     dauer
    0.06
     כבר
    0.06
     additional
    0.06
    優先
    0.06
    Activations Density 0.008%

    No Known Activations