© 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. 117031
    Prev
    Next
    INDEX
    Explanations

    hiring, seeking, building, announcing, solar energy

    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
     faaliyet
    -0.06
     jef
    -0.06
     optional
    -0.06
     genuine
    -0.06
     a
    -0.06
    新
    -0.06
     meiner
    -0.06
    aptop
    -0.06
     actual
    -0.05
    Optional
    -0.05
    POSITIVE LOGITS
     এই
    0.07
     Kazakhstan
    0.06
    นี้
    0.06
     acum
    0.06
     இந்த
    0.06
     этом
    0.06
     этот
    0.06
     extremos
    0.06
     خود
    0.06
     kommt
    0.06
    Activations Density 0.001%

    No Known Activations