© 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. 117181
    Prev
    Next
    INDEX
    Explanations

    programming languages

    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
     activa
    -0.06
    就有
    -0.06
     Managing
    -0.06
    meye
    -0.06
    ড়াই
    -0.05
    ong
    -0.05
     Anyway
    -0.05
     나누
    -0.05
     Collaboration
    -0.05
     delighted
    -0.05
    POSITIVE LOGITS
    ాల్సిన
    0.07
     సంగ
    0.06
    城市
    0.06
     solidly
    0.06
    docx
    0.06
     girdle
    0.06
    城市的
    0.06
     quarterback
    0.06
    hattan
    0.05
    クション
    0.05
    Activations Density 0.023%

    No Known Activations