© 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. 119370
    Prev
    Next
    INDEX
    Explanations

    code and technical 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
    一般的な
    -0.06
     لیے
    -0.06
     hauteur
    -0.06
     are
    -0.06
    ัญลักษณ์
    -0.06
    including
    -0.06
    Bitcoin
    -0.06
               
    -0.06
    MBOLS
    -0.06
    क्षणिक
    -0.06
    POSITIVE LOGITS
     july
    0.06
     Probate
    0.06
     ----->
    0.06
    findpost
    0.06
     عمر
    0.06
     organismo
    0.05
     manslaughter
    0.05
    未必
    0.05
     Erik
    0.05
     but
    0.05
    Activations Density 0.008%

    No Known Activations