© 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. 120917
    Prev
    Next
    INDEX
    Explanations

    childhood and upbringing details

    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
    Negative Logits
    havi
    -0.07
    Lifetime
    -0.06
     its
    -0.06
     제가
    -0.06
    prac
    -0.06
     is
    -0.06
     கிடைக்கும்
    -0.06
     trusty
    -0.06
     isn
    -0.06
     தனது
    -0.05
    POSITIVE LOGITS
     Norwich
    0.07
     unpleasant
    0.06
    แต่ละ
    0.06
     ting
    0.06
     ҳо
    0.06
    Each
    0.06
     जरी
    0.06
     Neither
    0.06
     anxiety
    0.06
    それぞれ
    0.06
    Activations Density 0.005%

    No Known Activations