© 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. 129006
    Prev
    Next
    INDEX
    Explanations

    long distance, building upon

    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
     Während
    -0.07
    期间
    -0.07
     கடல்
    -0.07
     während
    -0.07
    During
    -0.06
    increases
    -0.06
     podczas
    -0.06
     grasp
    -0.06
     northern
    -0.06
    Während
    -0.06
    POSITIVE LOGITS
     berbagai
    0.07
     serta
    0.07
     or
    0.06
    ,
    0.06
    或者是
    0.06
     dahil
    0.06
    son
    0.06
     approximately
    0.06
     আনু
    0.06
    ori
    0.05
    Activations Density 0.002%

    No Known Activations