© 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. 117595
    Prev
    Next
    INDEX
    Explanations

    students, staff, faculty

    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
    เด็ก
    -0.08
     vandaag
    -0.07
     physical
    -0.07
     çocuk
    -0.07
     heutigen
    -0.07
     negli
    -0.07
     children
    -0.07
     어린이
    -0.06
    alimentation
    -0.06
     físicos
    -0.06
    POSITIVE LOGITS
    経営
    0.06
     máximo
    0.06
     स्टाइलिश
    0.06
    "،
    0.06
     ปลา
    0.05
     karya
    0.05
    ป็น
    0.05
     unlink
    0.05
     المس
    0.05
     største
    0.05
    Activations Density 0.021%

    No Known Activations