© 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. 117755
    Prev
    Next
    INDEX
    Explanations

    specific

    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
     سایر
    -0.07
     đại
    -0.07
     நான்
    -0.07
     ഒന്നും
    -0.06
    その他の
    -0.06
     exacting
    -0.06
    釹
    -0.06
     ناخذ
    -0.06
     기타
    -0.06
     enclave
    -0.06
    POSITIVE LOGITS
     not
    0.07
    还
    0.06
     एवरेज
    0.06
     pond
    0.06
     retire
    0.06
    㶲
    0.06
     χρησιμοποι
    0.05
     especially
    0.05
    omat
    0.05
     in
    0.05
    Activations Density 0.009%

    No Known Activations