© 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. 128200
    Prev
    Next
    INDEX
    Explanations

    Al

    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
     recognised
    -0.06
     pequeña
    -0.06
    growth
    -0.06
     টিকে
    -0.06
    들은
    -0.06
    woods
    -0.06
     adapta
    -0.06
     growth
    -0.06
     proposed
    -0.06
     crescita
    -0.06
    POSITIVE LOGITS
     embl
    0.07
     ਵਿਚ
    0.06
     Inn
    0.06
     времен
    0.06
     anger
    0.06
     padded
    0.06
    तरी
    0.05
     *
    0.05
     bifur
    0.05
     extermin
    0.05
    Activations Density 0.010%

    No Known Activations