© 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. 116708
    Prev
    Next
    INDEX
    Explanations

    independent creative writing

    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
    SAFETY
    -0.07
     Nutzung
    -0.06
    生活
    -0.06
     повышен
    -0.06
    είου
    -0.06
     Safety
    -0.06
     military
    -0.06
     змен
    -0.06
     जोड़ने
    -0.06
     municipal
    -0.06
    POSITIVE LOGITS
     studio
    0.09
     studios
    0.09
     indie
    0.08
     mentor
    0.08
     Indie
    0.08
     स्टूडियो
    0.08
    Studio
    0.08
     studi
    0.07
     Studio
    0.07
    studio
    0.07
    Activations Density 0.017%

    No Known Activations