© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117230
    Prev
    Next
    INDEX
    Explanations

    tuple index

    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
     CODE
    -0.06
    ということは
    -0.06
     Kode
    -0.06
     ટે
    -0.06
    条件
    -0.06
    recl
    -0.06
     Código
    -0.06
     کوڈ
    -0.06
    ဖို့
    -0.06
     profe
    -0.06
    POSITIVE LOGITS
    Both
    0.06
     такие
    0.06
    both
    0.06
     proposed
    0.06
    atual
    0.06
     બાબ
    0.06
    Gd
    0.06
    Proposed
    0.06
    proposed
    0.05
    textTheme
    0.05
    Activations Density 0.033%

    No Known Activations