© 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. 118158
    Prev
    Next
    INDEX
    Explanations

    burial related places and words

    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
     vergleich
    -0.07
     wonderful
    -0.07
     മരണ
    -0.07
     similar
    -0.07
     사망
    -0.07
     прекра
    -0.07
    Similar
    -0.07
     necro
    -0.06
    丁寧
    -0.06
     काळजी
    -0.06
    POSITIVE LOGITS
     /(
    0.06
     能
    0.06
    FOUND
    0.06
    如图
    0.05
    Grow
    0.05
     Software
    0.05
    ড্ডা
    0.05
     couvre
    0.05
    During
    0.05
     mogen
    0.05
    Activations Density 0.009%

    No Known Activations