© 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. 116561
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

    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
    Though
    -0.06
    ː
    -0.06
    immediately
    -0.06
     :=
    -0.06
    轨
    -0.06
     трак
    -0.06
     ਇਸ
    -0.06
    though
    -0.06
     التالي
    -0.06
     defini
    -0.06
    POSITIVE LOGITS
     Deloitte
    0.07
     KPMG
    0.07
    britannien
    0.06
     changement
    0.06
     Range
    0.06
     illetve
    0.06
     cambiamento
    0.06
     questionnaire
    0.06
     anbef
    0.06
    大学生
    0.06
    Activations Density 0.059%

    No Known Activations