© 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. 120269
    Prev
    Next
    INDEX
    Explanations

    stringent, freedom, W, Dep

    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
     произво
    -0.06
    radical
    -0.06
     huid
    -0.06
     ছুরি
    -0.06
    LC
    -0.05
    就好
    -0.05
     жить
    -0.05
     veil
    -0.05
     criado
    -0.05
    veil
    -0.05
    POSITIVE LOGITS
     marav
    0.07
     வியா
    0.07
     checkIf
    0.07
     Universities
    0.06
    iklet
    0.06
     compatibility
    0.06
    "]').
    0.06
     उत्तरप्रदेश
    0.06
    Universidad
    0.06
    atakse
    0.06
    Activations Density 0.001%

    No Known Activations