© 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. 118989
    Prev
    Next
    INDEX
    Explanations

    why should

    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
     reactions
    -0.06
     liberté
    -0.06
     resultant
    -0.06
    هایت
    -0.06
     lascia
    -0.06
    reactions
    -0.06
     লোকটি
    -0.06
     resulting
    -0.05
     leaves
    -0.05
     صاف
    -0.05
    POSITIVE LOGITS
     convince
    0.07
     erhö
    0.06
     motto
    0.06
     differentiator
    0.06
     투자
    0.06
     justifica
    0.06
     justify
    0.06
     convinc
    0.06
     جسے
    0.06
     justification
    0.06
    Activations Density 0.058%

    No Known Activations