© 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. 130211
    Prev
    Next
    INDEX
    Explanations

    range of

    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
     সকল
    -0.07
    故事
    -0.06
     сеть
    -0.06
     defines
    -0.06
    clearly
    -0.06
     define
    -0.06
     womans
    -0.06
    defines
    -0.06
     biedt
    -0.06
     ყველა
    -0.06
    POSITIVE LOGITS
     officiating
    0.06
    effective
    0.06
    Without
    0.06
    Effective
    0.06
     Without
    0.06
     “
    0.06
    Learn
    0.05
    িয়ন
    0.05
     elabor
    0.05
     głów
    0.05
    Activations Density 0.016%

    No Known Activations