© 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. 116489
    Prev
    Next
    INDEX
    Explanations

    code browser structure functional

    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
     caused
    -0.06
     доктор
    -0.06
    োক
    -0.06
     لندن
    -0.06
     properly
    -0.06
     незна
    -0.06
     వలన
    -0.06
     경우에는
    -0.06
     вигляді
    -0.06
    freeze
    -0.06
    POSITIVE LOGITS
    িসহ
    0.06
     across
    0.06
     denominators
    0.06
     공개
    0.06
    🏖
    0.06
    jerne
    0.06
     внутреннего
    0.06
     OutputStream
    0.06
    OutputStream
    0.06
     ചെയ്യുന്ന
    0.06
    Activations Density 0.002%

    No Known Activations