© 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. 120774
    Prev
    Next
    INDEX
    Explanations

    make it" or "make a"

    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
    與
    -0.07
    return
    -0.07
     всех
    -0.06
     รัก
    -0.06
    十叁章
    -0.06
     Bhubaneswar
    -0.06
     backup
    -0.06
    Oops
    -0.06
     Backbone
    -0.06
    与
    -0.06
    POSITIVE LOGITS
     significativo
    0.06
     significativa
    0.06
    চ্ছেন
    0.06
     모르
    0.06
    boldsymbol
    0.06
     vivido
    0.06
     Coefficients
    0.06
     динами
    0.06
     determinante
    0.06
     significative
    0.05
    Activations Density 0.002%

    No Known Activations