© 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. 118077
    Prev
    Next
    INDEX
    Explanations

    technical terms like analysis, completeness, capabilities, extraction

    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
     perhaps
    -0.08
    perhaps
    -0.08
     впечат
    -0.07
     impressive
    -0.07
    getClient
    -0.07
     maybe
    -0.07
     segera
    -0.07
     misschien
    -0.07
     vielleicht
    -0.07
     nếu
    -0.07
    POSITIVE LOGITS
    訓練
    0.06
     designed
    0.06
     தடுக்க
    0.06
    👮
    0.06
    This
    0.06
     allows
    0.06
     restricted
    0.06
    🌃
    0.06
     সরানো
    0.06
    🚧
    0.06
    Activations Density 0.001%

    No Known Activations