© 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. 128377
    Prev
    Next
    INDEX
    Explanations

    initials and abbreviations

    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
     solchen
    -0.07
     such
    -0.06
     như
    -0.06
    Often
    -0.06
     таких
    -0.06
     الحصول
    -0.06
    このように
    -0.06
     frequently
    -0.06
     souvent
    -0.06
     ziet
    -0.06
    POSITIVE LOGITS
     despite
    0.06
     unaffected
    0.06
     unchanged
    0.06
     несмотря
    0.06
     هنگام
    0.06
    -
    0.06
     defining
    0.06
     nonostante
    0.05
     antigüedad
    0.05
     ƙ
    0.05
    Activations Density 0.001%

    No Known Activations