© 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. 120402
    Prev
    Next
    INDEX
    Explanations

    named entities and 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
     खिल
    -0.06
    就已经
    -0.06
     July
    -0.06
     June
    -0.06
     daripada
    -0.06
    July
    -0.06
     August
    -0.06
     matchup
    -0.06
    淤
    -0.06
     rival
    -0.06
    POSITIVE LOGITS
     femmes
    0.07
     swift
    0.07
     maksud
    0.06
     enriched
    0.06
     with
    0.06
     personel
    0.06
    த்துடன்
    0.06
    ⮕
    0.06
     सेक्सी
    0.06
    elled
    0.06
    Activations Density 0.001%

    No Known Activations