© 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. 130161
    Prev
    Next
    INDEX
    Explanations

    skill level or quality words

    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
    Goals
    -0.06
    ersch
    -0.06
     عندهم
    -0.06
     लाइफ
    -0.06
    goals
    -0.06
    丧
    -0.06
     Goals
    -0.06
     передба
    -0.05
    环保
    -0.05
    方式
    -0.05
    POSITIVE LOGITS
     novice
    0.08
     beginners
    0.07
     illustrious
    0.06
     geeignet
    0.06
     masterpiece
    0.06
     untrained
    0.06
    petition
    0.06
     expert
    0.06
     rookie
    0.06
     novices
    0.06
    Activations Density 0.067%

    No Known Activations