© 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. 117796
    Prev
    Next
    INDEX
    Explanations

    metadata headers

    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
     is
    -0.07
     during
    -0.07
     During
    -0.07
    During
    -0.06
     wordt
    -0.06
     OB
    -0.06
     ಉಪಯೋಗ
    -0.06
    Ꮲ
    -0.06
     uses
    -0.05
     Fif
    -0.05
    POSITIVE LOGITS
    都已经
    0.07
     そして
    0.06
    하지만
    0.06
    更高
    0.06
     त्यांचे
    0.06
     jejich
    0.06
     того
    0.06
     their
    0.06
    그러나
    0.06
     nende
    0.06
    Activations Density 0.001%

    No Known Activations