© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 116634
    Prev
    Next
    INDEX
    Explanations

    field conditions and environment

    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
     কাজটি
    -0.08
    それでも
    -0.06
     successes
    -0.06
     വിജയ
    -0.06
     கை
    -0.06
     வெற்றி
    -0.06
     existing
    -0.06
     rewarding
    -0.05
     linkages
    -0.05
    german
    -0.05
    POSITIVE LOGITS
    アクセサリー
    0.06
     khắp
    0.06
     அச்ச
    0.06
     गन्ना
    0.06
     особы
    0.06
    ་་
    0.06
     zoals
    0.06
     इनके
    0.06
     특
    0.06
     ecclesiastical
    0.06
    Activations Density 0.002%

    No Known Activations