© 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. 120754
    Prev
    Next
    INDEX
    Explanations

    code construction

    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
     amazing
    -0.07
    それぞれの
    -0.06
    ),
    -0.06
     moż
    -0.06
     novedades
    -0.06
     sobie
    -0.06
    Amazing
    -0.06
     AMAZING
    -0.06
    这两
    -0.06
    arına
    -0.06
    POSITIVE LOGITS
     [(
    0.06
     dmg
    0.06
    损伤
    0.06
    dropDown
    0.06
    停车
    0.06
    ingt
    0.05
     Chancen
    0.05
     انه
    0.05
     shutdowns
    0.05
     española
    0.05
    Activations Density 0.001%

    No Known Activations