© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130519
    Prev
    Next
    INDEX
    Explanations

    package names and versions

    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
     these
    -0.07
     diesen
    -0.07
     dieser
    -0.06
     denen
    -0.06
    らかじめ
    -0.06
    这类
    -0.06
     αυτές
    -0.06
     okvir
    -0.06
     длиной
    -0.06
     diesem
    -0.06
    POSITIVE LOGITS
     not
    0.07
     nonostante
    0.07
     være
    0.06
    反而
    0.06
     Moreover
    0.06
     include
    0.06
    Moreover
    0.06
     Furthermore
    0.06
     instantaneously
    0.06
     परस्पर
    0.06
    Activations Density 0.005%

    No Known Activations