© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130710
    Prev
    Next
    INDEX
    Explanations

    called to be

    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
     corneal
    -0.07
    戦争
    -0.06
     deseos
    -0.06
     যতটা
    -0.06
     hoped
    -0.06
    これからも
    -0.06
     semoga
    -0.06
     abstrak
    -0.06
     injecting
    -0.06
     בעי
    -0.06
    POSITIVE LOGITS
     optional
    0.07
     recent
    0.07
    recent
    0.06
    ለጠ
    0.06
     bestowed
    0.06
     spender
    0.06
     equipped
    0.06
    optional
    0.06
     elaborate
    0.06
    ალი
    0.06
    Activations Density 0.004%

    No Known Activations