© 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. 116099
    Prev
    Next
    INDEX
    Explanations

    programming construct names

    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
    ,
    -0.07
    ’’
    -0.07
    ]
    -0.06
    ipur
    -0.06
    )
    -0.06
    outs
    -0.06
    פתח
    -0.06
    √
    -0.06
     değil
    -0.06
    ூரில்
    -0.06
    POSITIVE LOGITS
    ↵
    0.07
     Judaism
    0.06
     without
    0.06
     estimations
    0.06
    sick
    0.06
     besonders
    0.06
     podendo
    0.06
     زیر
    0.06
     جنس
    0.06
     나머지
    0.06
    Activations Density 0.007%

    No Known Activations