© 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. 120794
    Prev
    Next
    INDEX
    Explanations

    litigation

    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
     seldom
    -0.07
     ರೀ
    -0.06
     gleiche
    -0.06
     Are
    -0.06
     पिच
    -0.06
    യിലൂടെ
    -0.06
     claim
    -0.06
     complementarity
    -0.06
     cid
    -0.06
     Sometimes
    -0.06
    POSITIVE LOGITS
     অতিথি
    0.06
     Ducati
    0.06
    迷
    0.06
     Pediatrics
    0.05
     которое
    0.05
    ೫
    0.05
    を集
    0.05
     consolidated
    0.05
     rescheduling
    0.05
     multitud
    0.05
    Activations Density 0.008%

    No Known Activations