© 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. 130467
    Prev
    Next
    INDEX
    Explanations

    hamstring niggle

    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
     zare
    -0.07
    Lets
    -0.07
     can
    -0.06
     oben
    -0.06
    цин
    -0.06
     Lets
    -0.06
     রয়েছে
    -0.06
     descansar
    -0.06
     može
    -0.06
     देयर
    -0.06
    POSITIVE LOGITS
     part
    0.07
     travaille
    0.06
     Method
    0.06
     an
    0.06
    のために
    0.06
     energetically
    0.06
    粋
    0.06
    araham
    0.06
    regel
    0.06
     contributing
    0.06
    Activations Density 0.036%

    No Known Activations