© 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. 120498
    Prev
    Next
    INDEX
    Explanations

    programming keywords and struct members

    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
     threshold
    -0.07
     sendiri
    -0.07
     ambientales
    -0.06
     إذا
    -0.06
     другое
    -0.06
     Этот
    -0.06
    οντας
    -0.06
    เรา
    -0.06
     дъл
    -0.06
     것이다
    -0.06
    POSITIVE LOGITS
     DEFAULT
    0.06
     You
    0.06
     which
    0.05
     Royal
    0.05
     amyl
    0.05
     विफल
    0.05
     Nar
    0.05
    ley
    0.05
     स्टेट
    0.05
    Bau
    0.05
    Activations Density 0.001%

    No Known Activations