© 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. 118884
    Prev
    Next
    INDEX
    Explanations

    familiar or unfamiliar concepts

    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
    前往
    -0.06
     relatively
    -0.06
     loro
    -0.06
     estuvieron
    -0.06
     naï
    -0.06
     більш
    -0.06
     Bigger
    -0.06
     साप
    -0.06
     blacks
    -0.06
     ট্যাক
    -0.05
    POSITIVE LOGITS
     at
    0.07
     समृद्ध
    0.06
    ittance
    0.06
    行
    0.06
     используется
    0.06
    illian
    0.06
    aminophen
    0.05
     включа
    0.05
    を行う
    0.05
     dùng
    0.05
    Activations Density 0.014%

    No Known Activations