© 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. 119850
    Prev
    Next
    INDEX
    Explanations

    circuit or case identifiers

    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
     minim
    -0.06
     Cic
    -0.06
    startTime
    -0.05
     moldings
    -0.05
     प्रारंभ
    -0.05
     fished
    -0.05
    ünd
    -0.05
    yj
    -0.05
    standards
    -0.05
    ர்க
    -0.05
    POSITIVE LOGITS
     the
    0.08
     a
    0.08
     some
    0.07
     an
    0.07
     относится
    0.06
     на
    0.06
     another
    0.06
    ‌లు
    0.06
     rush
    0.06
    這麼
    0.06
    Activations Density 0.004%

    No Known Activations