© 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. 130953
    Prev
    Next
    INDEX
    Explanations

    Celiac, Q&A, Carbon nanotubes

    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
     topics
    -0.07
    内容は
    -0.07
     Similarly
    -0.06
    苷
    -0.06
    と同様
    -0.06
     případ
    -0.06
     마찬가지
    -0.06
     dazu
    -0.06
    Similarly
    -0.06
    と同じ
    -0.06
    POSITIVE LOGITS
     COMB
    0.06
    2
    0.06
     abnorm
    0.05
     Nissan
    0.05
     Announced
    0.05
    र्जर
    0.05
     Dio
    0.05
     certainly
    0.05
    想想
    0.05
    Aaron
    0.05
    Activations Density 0.001%

    No Known Activations