© 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. 130460
    Prev
    Next
    INDEX
    Explanations

    consequences of being untreated

    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
    চো
    -0.06
    \%$
    -0.06
     inception
    -0.06
    \%
    -0.06
    ನ್‌
    -0.06
     Creations
    -0.06
     WorldCat
    -0.05
    遺
    -0.05
    sinx
    -0.05
    अधिकांश
    -0.05
    POSITIVE LOGITS
     thằng
    0.07
     celestial
    0.06
    ходила
    0.06
     मुताबिक
    0.06
     кораб
    0.06
    chad
    0.06
     hohen
    0.06
     walked
    0.05
    बिट
    0.05
     quickly
    0.05
    Activations Density 0.007%

    No Known Activations