© 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. 129076
    Prev
    Next
    INDEX
    Explanations

    license details or information

    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
     scripture
    -0.06
     on
    -0.06
     that
    -0.06
     due
    -0.06
    כז
    -0.06
     ሙ
    -0.06
    fisherman
    -0.05
     μας
    -0.05
     досто
    -0.05
    我们需要
    -0.05
    POSITIVE LOGITS
    更多的
    0.06
    िटर
    0.06
     contactos
    0.06
     Bolet
    0.06
     বিশেষজ্ঞদের
    0.06
     pretended
    0.06
    Uses
    0.06
     sucede
    0.05
     waarin
    0.05
    烛
    0.05
    Activations Density 0.001%

    No Known Activations