© 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. 116200
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
     Hence
    -0.06
    ！！
    -0.06
     திரும
    -0.06
     Senado
    -0.06
     imam
    -0.06
     С
    -0.06
    ("",
    -0.06
    ❗
    -0.06
     bisexual
    -0.06
     under
    -0.05
    POSITIVE LOGITS
    に必要な
    0.07
     vielleicht
    0.07
     delivers
    0.07
     रिश्वत
    0.06
    很简单
    0.06
     delivered
    0.06
     will
    0.06
    gathered
    0.06
    ?]
    0.06
     misschien
    0.06
    Activations Density 0.002%

    No Known Activations