© 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. 120653
    Prev
    Next
    INDEX
    Explanations

    chemical structure notations

    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
     by
    -0.07
     लिखकर
    -0.06
     senza
    -0.06
     juge
    -0.06
     உணவு
    -0.06
     conformément
    -0.06
    を使って
    -0.06
     llevando
    -0.06
     Placing
    -0.06
     Conform
    -0.06
    POSITIVE LOGITS
    Peter
    0.06
     konkret
    0.05
    eliness
    0.05
     bonus
    0.05
     gentlemen
    0.05
     sowie
    0.05
     Gerald
    0.05
    以及
    0.05
    тому
    0.05
     betre
    0.05
    Activations Density 0.006%

    No Known Activations