© 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. 119289
    Prev
    Next
    INDEX
    Explanations

    coli

    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
    ほとんど
    -0.07
    다른
    -0.07
     다른
    -0.06
    WELCOME
    -0.06
     garb
    -0.06
     wardrobe
    -0.06
     for
    -0.06
    其他
    -0.06
    Welcome
    -0.06
    其他的
    -0.06
    POSITIVE LOGITS
     busting
    0.06
     tersebut
    0.06
    TEST
    0.06
     skala
    0.06
    qc
    0.06
     zählen
    0.06
     importantly
    0.06
     rightfully
    0.05
     required
    0.05
    的
    0.05
    Activations Density 0.028%

    No Known Activations