© 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. 120054
    Prev
    Next
    INDEX
    Explanations

    either then or synonyms

    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
    僅
    -0.07
     parlare
    -0.06
     只
    -0.06
     aka
    -0.06
    AKA
    -0.06
    现
    -0.06
     தாக்கு
    -0.06
    只
    -0.06
     afirmar
    -0.06
     Supportive
    -0.06
    POSITIVE LOGITS
     then
    0.08
     entonces
    0.07
    then
    0.07
    tedy
    0.06
    yst
    0.06
    Sch
    0.06
    Then
    0.06
     тогда
    0.06
    ..........
    0.06
     então
    0.06
    Activations Density 0.078%

    No Known Activations