© 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. 120053
    Prev
    Next
    INDEX
    Explanations

    method calls

    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
    作为一个
    -0.07
     있는지
    -0.06
     menunjukkan
    -0.06
     calific
    -0.06
    ナス
    -0.06
     hacen
    -0.06
     europé
    -0.06
     Supernatural
    -0.06
     reve
    -0.06
     באופן
    -0.06
    POSITIVE LOGITS
    ).
    0.07
    ch
    0.06
    。
    0.06
    .
    0.06
    기와
    0.06
    尽管
    0.06
    除此之外
    0.06
    此外
    0.06
    与
    0.06
     అనంతరం
    0.06
    Activations Density 0.002%

    No Known Activations