© 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. 117915
    Prev
    Next
    INDEX
    Explanations

    navigating back to previously seen

    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
     जिसको
    -0.06
     Ste
    -0.06
    6
    -0.06
     T
    -0.06
    xtime
    -0.05
    ូវ
    -0.05
     F
    -0.05
    如何
    -0.05
    9
    -0.05
    িট
    -0.05
    POSITIVE LOGITS
    ρίζ
    0.07
     Гуляць
    0.07
    lerine
    0.07
    ධාන
    0.06
     madrugada
    0.06
     digitar
    0.06
     удиви
    0.06
     décembre
    0.06
    ೋಗ
    0.06
     oorlog
    0.06
    Activations Density 0.001%

    No Known Activations