© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118467
    Prev
    Next
    INDEX
    Explanations

    hired, commissioned, or requested

    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
     regulations
    -0.08
     groundbreaking
    -0.07
     ordinances
    -0.07
     ulteriori
    -0.06
     cardí
    -0.06
     inglês
    -0.06
     attendant
    -0.06
     Sniper
    -0.06
    㽞
    -0.06
    ಾರ್
    -0.06
    POSITIVE LOGITS
     فقد
    0.06
    画面
    0.06
    <b>
    0.05
    kem
    0.05
     situation
    0.05
    して
    0.05
    almost
    0.05
    漠
    0.05
     வளாக
    0.05
    පත්
    0.05
    Activations Density 0.004%

    No Known Activations