© 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. 129005
    Prev
    Next
    INDEX
    Explanations

    research questions, aims, hypotheses

    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
     intermin
    -0.06
     সম্র
    -0.06
    これから
    -0.06
     مقاب
    -0.06
     এখনো
    -0.06
     impractic
    -0.06
    Beans
    -0.06
     нынеш
    -0.06
    咫
    -0.06
     युवती
    -0.06
    POSITIVE LOGITS
    back
    0.06
     back
    0.06
                
    0.06
     ماشي
    0.06
     queria
    0.06
     Red
    0.06
     разделить
    0.06
     EFFECTS
    0.06
     другое
    0.06
    りたい
    0.06
    Activations Density 0.008%

    No Known Activations