© 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. 129451
    Prev
    Next
    INDEX
    Explanations

    `false`, `true`, `none`

    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
    hane
    -0.07
     frank
    -0.06
    éph
    -0.06
     Quindi
    -0.06
     তিন
    -0.06
     clearest
    -0.06
     clickable
    -0.05
    お願いいたします
    -0.05
     kei
    -0.05
     mosa
    -0.05
    POSITIVE LOGITS
     jetzt
    0.06
     şimdi
    0.06
     ఇప్పుడు
    0.06
     ውስ
    0.06
     сега
    0.06
    anzia
    0.06
    승
    0.06
     now
    0.06
    現在
    0.06
    역시
    0.06
    Activations Density 0.001%

    No Known Activations