© 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. 120525
    Prev
    Next
    INDEX
    Explanations

    USB and php code snippets

    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
     случаях
    -0.06
     formular
    -0.06
     Yang
    -0.06
     của
    -0.06
     catap
    -0.06
     YOUR
    -0.06
     PLUS
    -0.06
    imų
    -0.06
     우리의
    -0.06
    ்ப்ப
    -0.06
    POSITIVE LOGITS
     αυτή
    0.07
     such
    0.06
    ㅓ
    0.06
    󠁬
    0.06
    這種
    0.06
    决策
    0.06
     because
    0.06
     baryon
    0.06
    Sob
    0.06
    
    0.05
    Activations Density 0.001%

    No Known Activations