© 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. 128219
    Prev
    Next
    INDEX
    Explanations

    male genitalglobal productioncorrection to

    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
     दिग्गज
    -0.07
    ために
    -0.07
     आणि
    -0.06
     जबरदस्त
    -0.06
     determination
    -0.06
     determine
    -0.06
     مختلفة
    -0.06
     drastically
    -0.06
    期間
    -0.06
     are
    -0.06
    POSITIVE LOGITS
    如下图
    0.06
     embarazo
    0.06
     jardins
    0.06
     adatto
    0.06
    seat
    0.06
     sorpre
    0.06
     the
    0.06
     vorgesehen
    0.06
    视觉
    0.06
    Seat
    0.06
    Activations Density 0.002%

    No Known Activations