© 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. 127934
    Prev
    Next
    INDEX
    Explanations

    URL ports and versions

    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
     interestingly
    -0.07
     conserving
    -0.07
     shockingly
    -0.06
     тоже
    -0.06
    所属
    -0.06
     brutality
    -0.06
     dessous
    -0.06
     несколь
    -0.06
     phenolic
    -0.06
    辰
    -0.06
    POSITIVE LOGITS
    ‌ی
    0.06
    仅
    0.06
     niż
    0.06
     Klo
    0.06
    僅
    0.06
    이었
    0.05
     любые
    0.05
     práctica
    0.05
     ব্যর্থ
    0.05
    either
    0.05
    Activations Density 0.005%

    No Known Activations