© 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. 119231
    Prev
    Next
    INDEX
    Explanations

    constructor arguments

    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
     dependency
    -0.06
     ஞ
    -0.05
    ？
    -0.05
    网
    -0.05
     busiest
    -0.05
    ?’
    -0.05
    sun
    -0.05
    platform
    -0.05
     écr
    -0.05
     ఉపయోగ
    -0.05
    POSITIVE LOGITS
    情報
    0.07
    Nếu
    0.07
    ುತ್ತೇವೆ
    0.07
     oni
    0.06
     gauss
    0.06
     промышлен
    0.06
     MNC
    0.06
    INDUSTRIAL
    0.06
     diciembre
    0.06
    Пол
    0.06
    Activations Density 0.011%

    No Known Activations