© 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. 116179
    Prev
    Next
    INDEX
    Explanations

    programming error messages

    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
     rien
    -0.06
     Bina
    -0.06
     niets
    -0.06
    irken
    -0.06
     succession
    -0.06
    انی
    -0.05
     nic
    -0.05
     protecting
    -0.05
    Neither
    -0.05
     successors
    -0.05
    POSITIVE LOGITS
     DIAG
    0.06
    簡易
    0.06
    舢
    0.06
     nearest
    0.06
    SUFFIX
    0.06
     DISPLAYS
    0.06
     Bankr
    0.06
     ука
    0.06
     Ubud
    0.06
    演讲
    0.05
    Activations Density 0.002%

    No Known Activations