© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 115949
    Prev
    Next
    INDEX
    Explanations

    success and need

    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
    Negative Logits
     사용
    -0.08
     jeho
    -0.08
     Tuesday
    -0.07
     jejich
    -0.07
     그의
    -0.07
    Tuesday
    -0.07
     Monday
    -0.07
    Wednesday
    -0.07
    满意
    -0.07
     Wednesday
    -0.07
    POSITIVE LOGITS
     success
    0.06
     réussir
    0.06
    戦略
    0.06
     modest
    0.06
     foothold
    0.06
    ಶಸ್
    0.06
     strategic
    0.06
     difficulty
    0.06
    コツ
    0.06
     successes
    0.06
    Activations Density 0.011%

    No Known Activations